Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1177. Min Range: -8.1177
Max Act: 8.1177. Min Act: -0.1700
Data Index: 7712069 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.8989. Min Act: -0.1700
Data Index: 2482656 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.8989. Min Act: -0.1700
Data Index: 7079224 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.8364. Min Act: -0.1700
Data Index: 8374535 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.8052. Min Act: -0.1700
Data Index: 5891988 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.7114. Min Act: -0.1700
Data Index: 4625064 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.7114. Min Act: -0.1700
Data Index: 3655972 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.7114. Min Act: -0.1700
Data Index: 4661380 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.7114. Min Act: -0.1700
Data Index: 7461656 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.6802. Min Act: -0.1700
Data Index: 8307476 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.6489. Min Act: -0.1700
Data Index: 7403658 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.6177. Min Act: -0.1700
Data Index: 1122302 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.6177. Min Act: -0.1700
Data Index: 6815582 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.6177. Min Act: -0.1700
Data Index: 5385630 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.5864. Min Act: -0.1700
Data Index: 3928608 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.5864. Min Act: -0.1700
Data Index: 5846808 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.6177. Min Act: -0.1700
Data Index: 92092 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.5239. Min Act: -0.1700
Data Index: 1265958 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.4927. Min Act: -0.1700
Data Index: 6339957 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1177. Min Range: -8.1177
Max Act: 7.4927. Min Act: -0.1700
Data Index: 3577848 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19