Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.4967. Min Act: -0.1700
Data Index: 5293425 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.3404. Min Act: -0.1700
Data Index: 2265853 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.2779. Min Act: -0.1700
Data Index: 5672104 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.2467. Min Act: -0.1700
Data Index: 571070 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.1217. Min Act: -0.1700
Data Index: 201557 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.1217. Min Act: -0.1700
Data Index: 8072760 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.0904. Min Act: -0.1700
Data Index: 4166423 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.1217. Min Act: -0.1700
Data Index: 3971000 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.0592. Min Act: -0.1700
Data Index: 55987 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.0904. Min Act: -0.1700
Data Index: 1696018 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.0592. Min Act: -0.1700
Data Index: 4831658 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.0592. Min Act: -0.1700
Data Index: 6270283 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4967. Min Range: -7.4967
Max Act: 7.0279. Min Act: -0.1700
Data Index: 6183596 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9967. Min Act: -0.1700
Data Index: 1947854 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9967. Min Act: -0.1700
Data Index: 5127857 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9967. Min Act: -0.1700
Data Index: 5303128 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9654. Min Act: -0.1700
Data Index: 218980 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9654. Min Act: -0.1700
Data Index: 2494073 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9342. Min Act: -0.1700
Data Index: 2742054 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4967. Min Range: -7.4967
Max Act: 6.9342. Min Act: -0.1700
Data Index: 3628898 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19