Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1663 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.6216. Min Act: -0.1700
Data Index: 426871 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.5903. Min Act: -0.1700
Data Index: 4868899 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4966. Min Act: -0.1700
Data Index: 5928183 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4966. Min Act: -0.1700
Data Index: 5577810 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4341. Min Act: -0.1700
Data Index: 2544584 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4653. Min Act: -0.1700
Data Index: 1172466 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4653. Min Act: -0.1700
Data Index: 492914 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4028. Min Act: -0.1700
Data Index: 492913 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4028. Min Act: -0.1700
Data Index: 3883124 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.4341. Min Act: -0.1700
Data Index: 5183644 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3716. Min Act: -0.1700
Data Index: 2376138 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3716. Min Act: -0.1700
Data Index: 836348 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3716. Min Act: -0.1700
Data Index: 6354707 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3091. Min Act: -0.1700
Data Index: 4213910 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3403. Min Act: -0.1700
Data Index: 3646944 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3091. Min Act: -0.1700
Data Index: 2852306 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3716. Min Act: -0.1700
Data Index: 3870547 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3091. Min Act: -0.1700
Data Index: 3335599 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3403. Min Act: -0.1700
Data Index: 6919854 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6216. Min Range: -5.6216
Max Act: 5.3091. Min Act: -0.1700
Data Index: 6248461 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19