Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.6205. Min Act: -0.1700
Data Index: 1581548 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.3705. Min Act: -0.1700
Data Index: 6276260 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.3705. Min Act: -0.1700
Data Index: 6033957 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.3080. Min Act: -0.1700
Data Index: 5427371 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.1205. Min Act: -0.1700
Data Index: 5847831 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.1205. Min Act: -0.1700
Data Index: 3831805 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.1205. Min Act: -0.1700
Data Index: 8357363 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.0580. Min Act: -0.1700
Data Index: 3114394 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.0580. Min Act: -0.1700
Data Index: 667362 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6205. Min Range: -8.6205
Max Act: 8.0580. Min Act: -0.1700
Data Index: 7883681 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 4291225 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 11766 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 6617892 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 1440842 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 6865223 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9330. Min Act: -0.1700
Data Index: 6035430 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9330. Min Act: -0.1700
Data Index: 7764907 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9330. Min Act: -0.1700
Data Index: 7571815 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9330. Min Act: -0.1700
Data Index: 7537704 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6205. Min Range: -8.6205
Max Act: 7.9330. Min Act: -0.1700
Data Index: 7055502 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19