Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.6590. Min Act: -0.1700
Data Index: 543069 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.6590. Min Act: -0.1700
Data Index: 4417436 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.6590. Min Act: -0.1700
Data Index: 7508661 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.5340. Min Act: -0.1700
Data Index: 8232104 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.4715. Min Act: -0.1700
Data Index: 7078464 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.4715. Min Act: -0.1700
Data Index: 5424644 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.3465. Min Act: -0.1700
Data Index: 4533803 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.3465. Min Act: -0.1700
Data Index: 1991147 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.3465. Min Act: -0.1700
Data Index: 1951317 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.3465. Min Act: -0.1700
Data Index: 3555916 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.3465. Min Act: -0.1700
Data Index: 5888299 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.2215. Min Act: -0.1700
Data Index: 1258134 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.2840. Min Act: -0.1700
Data Index: 860094 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.3465. Min Act: -0.1700
Data Index: 191465 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.2840. Min Act: -0.1700
Data Index: 6263941 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.2840. Min Act: -0.1700
Data Index: 216735 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.1590. Min Act: -0.1700
Data Index: 7934539 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.2840. Min Act: -0.1700
Data Index: 2582933 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.1590. Min Act: -0.1700
Data Index: 2001378 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.6590. Min Range: -14.6590
Max Act: 14.1590. Min Act: -0.1700
Data Index: 1670378 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19