Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6802. Min Range: -7.6802
Max Act: 7.6802. Min Act: -0.1700
Data Index: 2511410 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6802. Min Range: -7.6802
Max Act: 7.4302. Min Act: -0.1700
Data Index: 157624 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6802. Min Range: -7.6802
Max Act: 7.3365. Min Act: -0.1700
Data Index: 8451256 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6802. Min Range: -7.6802
Max Act: 7.3052. Min Act: -0.1700
Data Index: 3929019 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6802. Min Range: -7.6802
Max Act: 7.0865. Min Act: -0.1700
Data Index: 6716579 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6802. Min Range: -7.6802
Max Act: 7.0552. Min Act: -0.1700
Data Index: 5555027 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.9302. Min Act: -0.1700
Data Index: 2263394 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.8677. Min Act: -0.1700
Data Index: 5269608 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.8365. Min Act: -0.1700
Data Index: 6876949 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.8052. Min Act: -0.1700
Data Index: 6003228 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.7427. Min Act: -0.1700
Data Index: 2643976 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.6802. Min Act: -0.1700
Data Index: 652137 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.6490. Min Act: -0.1700
Data Index: 4889806 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.6177. Min Act: -0.1697
Data Index: 4643297 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.5240. Min Act: -0.1700
Data Index: 2251151 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.5240. Min Act: -0.1700
Data Index: 754427 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.4927. Min Act: -0.1700
Data Index: 5903493 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.4927. Min Act: -0.1700
Data Index: 1102326 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.4615. Min Act: -0.1700
Data Index: 4752316 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6802. Min Range: -7.6802
Max Act: 6.3990. Min Act: -0.1700
Data Index: 2480041 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19