Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.2368. Min Act: -0.1700
Data Index: 3857726 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.2368. Min Act: -0.1700
Data Index: 8495736 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.1431. Min Act: -0.1700
Data Index: 8146066 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.1431. Min Act: -0.1700
Data Index: 2681372 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.1431. Min Act: -0.1700
Data Index: 1037126 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.1118. Min Act: -0.1700
Data Index: 5014336 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.1118. Min Act: -0.1700
Data Index: 6555470 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.0806. Min Act: -0.1700
Data Index: 7407462 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.0493. Min Act: -0.1700
Data Index: 3099746 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2368. Min Range: -6.2368
Max Act: 6.0181. Min Act: -0.1700
Data Index: 4545586 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9868. Min Act: -0.1700
Data Index: 8447391 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9868. Min Act: -0.1700
Data Index: 4790856 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9868. Min Act: -0.1700
Data Index: 6578248 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9868. Min Act: -0.1700
Data Index: 4636072 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9868. Min Act: -0.1700
Data Index: 4050881 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9556. Min Act: -0.1700
Data Index: 2854803 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9868. Min Act: -0.1700
Data Index: 6771304 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9243. Min Act: -0.1700
Data Index: 2562473 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9556. Min Act: -0.1700
Data Index: 2572547 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2368. Min Range: -6.2368
Max Act: 5.9556. Min Act: -0.1700
Data Index: 4287347 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19