Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5162 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0358. Min Range: -6.0358
Max Act: 6.0358. Min Act: -0.1700
Data Index: 2398277 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.8170. Min Act: -0.1700
Data Index: 2049123 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.7858. Min Act: -0.1700
Data Index: 3242106 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.7545. Min Act: -0.1700
Data Index: 8488111 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.6608. Min Act: -0.1700
Data Index: 847307 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.6608. Min Act: -0.1700
Data Index: 1189623 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7695999 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.6295. Min Act: -0.1700
Data Index: 6104195 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5983. Min Act: -0.1700
Data Index: 7079111 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5983. Min Act: -0.1700
Data Index: 4348843 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5670. Min Act: -0.1700
Data Index: 1285184 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5983. Min Act: -0.1700
Data Index: 2744012 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5670. Min Act: -0.1700
Data Index: 5691387 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5670. Min Act: -0.1700
Data Index: 6146529 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5983. Min Act: -0.1700
Data Index: 1613545 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5670. Min Act: -0.1700
Data Index: 8393649 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5670. Min Act: -0.1700
Data Index: 3408456 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5358. Min Act: -0.1700
Data Index: 6478619 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5358. Min Act: -0.1700
Data Index: 3195680 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0358. Min Range: -6.0358
Max Act: 5.5358. Min Act: -0.1700
Data Index: 7302501 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19