Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5293. Min Range: -6.5293
Max Act: 6.5293. Min Act: -0.1700
Data Index: 5312153 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5293. Min Range: -6.5293
Max Act: 6.1543. Min Act: -0.1700
Data Index: 457547 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5293. Min Range: -6.5293
Max Act: 6.0606. Min Act: -0.1700
Data Index: 7922705 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.9981. Min Act: -0.1700
Data Index: 3376977 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.9668. Min Act: -0.1700
Data Index: 7898478 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.9668. Min Act: -0.1700
Data Index: 7761574 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.9668. Min Act: -0.1700
Data Index: 8607040 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.9356. Min Act: -0.1700
Data Index: 1864042 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.9356. Min Act: -0.1700
Data Index: 4295614 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8731. Min Act: -0.1700
Data Index: 2762452 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8731. Min Act: -0.1700
Data Index: 7059781 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8418. Min Act: -0.1700
Data Index: 2532039 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8418. Min Act: -0.1700
Data Index: 5892192 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8106. Min Act: -0.1700
Data Index: 6591890 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8418. Min Act: -0.1700
Data Index: 6140357 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4762595 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.8418. Min Act: -0.1700
Data Index: 3484605 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4723178 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4683846 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5293. Min Range: -6.5293
Max Act: 5.7793. Min Act: -0.1700
Data Index: 6162133 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19