Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.5989. Min Act: -0.1700
Data Index: 8035144 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4739. Min Act: -0.1700
Data Index: 8487528 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4739. Min Act: -0.1700
Data Index: 3858000 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4739. Min Act: -0.1700
Data Index: 56142 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4739. Min Act: -0.1700
Data Index: 754468 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4427. Min Act: -0.1700
Data Index: 7735733 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4427. Min Act: -0.1700
Data Index: 4442814 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4114. Min Act: -0.1700
Data Index: 4537833 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4114. Min Act: -0.1700
Data Index: 2084081 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.3802. Min Act: -0.1700
Data Index: 2334629 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.4114. Min Act: -0.1700
Data Index: 1608719 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.3489. Min Act: -0.1700
Data Index: 1766494 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2864. Min Act: -0.1700
Data Index: 8675075 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2551. Min Act: -0.1700
Data Index: 6269554 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2551. Min Act: -0.1700
Data Index: 2345094 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2864. Min Act: -0.1700
Data Index: 6976154 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2551. Min Act: -0.1700
Data Index: 6266734 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2551. Min Act: -0.1700
Data Index: 5613348 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2239. Min Act: -0.1700
Data Index: 3119458 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5989. Min Range: -4.5989
Max Act: 4.2239. Min Act: -0.1700
Data Index: 5975248 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19