Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0158. Min Range: -6.0158
Max Act: 6.0158. Min Act: -0.1700
Data Index: 3327224 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.9533. Min Act: -0.1700
Data Index: 6798724 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.9533. Min Act: -0.1700
Data Index: 6672675 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.9845. Min Act: -0.1700
Data Index: 7446541 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.9533. Min Act: -0.1700
Data Index: 6836568 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.9533. Min Act: -0.1700
Data Index: 1161863 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.8908. Min Act: -0.1700
Data Index: 5999065 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.8908. Min Act: -0.1700
Data Index: 8097331 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.8283. Min Act: -0.1700
Data Index: 3814898 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7970. Min Act: -0.1700
Data Index: 5814549 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7970. Min Act: -0.1700
Data Index: 2722125 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7658. Min Act: -0.1700
Data Index: 1129684 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7345. Min Act: -0.1700
Data Index: 4458118 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7345. Min Act: -0.1700
Data Index: 3006457 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7345. Min Act: -0.1700
Data Index: 471126 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7345. Min Act: -0.1700
Data Index: 6637788 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7033. Min Act: -0.1700
Data Index: 4388493 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7033. Min Act: -0.1700
Data Index: 4048149 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7033. Min Act: -0.1700
Data Index: 1822669 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0158. Min Range: -6.0158
Max Act: 5.7033. Min Act: -0.1700
Data Index: 3159630 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19