Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0427. Min Range: -6.0427
Max Act: 6.0427. Min Act: -0.1700
Data Index: 3297584 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.9802. Min Act: -0.1700
Data Index: 333828 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.9177. Min Act: -0.1700
Data Index: 7502543 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8864. Min Act: -0.1700
Data Index: 4090173 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.9177. Min Act: -0.1700
Data Index: 743876 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8864. Min Act: -0.1700
Data Index: 3180906 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8552. Min Act: -0.1700
Data Index: 3843364 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8552. Min Act: -0.1700
Data Index: 7217347 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8864. Min Act: -0.1700
Data Index: 6847300 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8239. Min Act: -0.1700
Data Index: 7152024 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7927. Min Act: -0.1700
Data Index: 685404 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.8239. Min Act: -0.1700
Data Index: 2438059 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7927. Min Act: -0.1700
Data Index: 7347624 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1021868 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7927. Min Act: -0.1700
Data Index: 8715465 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7614. Min Act: -0.1700
Data Index: 4567260 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7614. Min Act: -0.1700
Data Index: 2461613 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2141216 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7614. Min Act: -0.1700
Data Index: 5984988 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0427. Min Range: -6.0427
Max Act: 5.7927. Min Act: -0.1700
Data Index: 7589717 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19