Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1259. Min Range: -8.1259
Max Act: 8.1259. Min Act: -0.1700
Data Index: 4827718 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1259. Min Range: -8.1259
Max Act: 8.0947. Min Act: -0.1700
Data Index: 8179462 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1259. Min Range: -8.1259
Max Act: 8.0634. Min Act: -0.1700
Data Index: 2939531 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1259. Min Range: -8.1259
Max Act: 8.0634. Min Act: -0.1699
Data Index: 5947823 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.9384. Min Act: -0.1700
Data Index: 257782 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.8759. Min Act: -0.1700
Data Index: 1580990 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.8759. Min Act: -0.1700
Data Index: 1696030 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.8447. Min Act: -0.1700
Data Index: 8156288 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.8759. Min Act: -0.1700
Data Index: 1192876 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.7822. Min Act: -0.1700
Data Index: 1750243 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.7509. Min Act: -0.1700
Data Index: 3358961 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.7509. Min Act: -0.1700
Data Index: 7233076 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6572. Min Act: -0.1700
Data Index: 7003097 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6259. Min Act: -0.1700
Data Index: 3203559 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6572. Min Act: -0.1699
Data Index: 104836 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6572. Min Act: -0.1700
Data Index: 3426512 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6572. Min Act: -0.1682
Data Index: 5970459 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6572. Min Act: -0.1700
Data Index: 1390073 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.6259. Min Act: -0.1700
Data Index: 5224150 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1259. Min Range: -8.1259
Max Act: 7.5947. Min Act: -0.1700
Data Index: 420668 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19