Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.9646. Min Act: -0.1700
Data Index: 3643853 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.9333. Min Act: -0.1700
Data Index: 7171967 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.9021. Min Act: -0.1700
Data Index: 5731342 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.8708. Min Act: -0.1700
Data Index: 4565858 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.8708. Min Act: -0.1700
Data Index: 4678639 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.8396. Min Act: -0.1700
Data Index: 4184812 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.8083. Min Act: -0.1700
Data Index: 5779485 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.8396. Min Act: -0.1700
Data Index: 5548037 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.7771. Min Act: -0.1700
Data Index: 356780 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.8083. Min Act: -0.1700
Data Index: 474543 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.7458. Min Act: -0.1700
Data Index: 458928 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.7146. Min Act: -0.1700
Data Index: 2486180 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.7146. Min Act: -0.1700
Data Index: 1714530 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.6521. Min Act: -0.1700
Data Index: 4736738 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.6208. Min Act: -0.1700
Data Index: 7181109 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.5896. Min Act: -0.1700
Data Index: 1289023 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.6208. Min Act: -0.1700
Data Index: 3301785 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.5896. Min Act: -0.1700
Data Index: 5389355 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.6208. Min Act: -0.1700
Data Index: 8588827 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9646. Min Range: -6.9646
Max Act: 6.5896. Min Act: -0.1700
Data Index: 6516499 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19