Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0080. Min Range: -10.0080
Max Act: 10.0080. Min Act: -0.1700
Data Index: 6824906 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0080. Min Range: -10.0080
Max Act: 10.0080. Min Act: -0.1700
Data Index: 1042044 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.5705. Min Act: -0.1700
Data Index: 4976783 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.2580. Min Act: -0.1700
Data Index: 7023609 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.1955. Min Act: -0.1700
Data Index: 813488 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.1955. Min Act: -0.1700
Data Index: 969650 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.1330. Min Act: -0.1700
Data Index: 4647241 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.1330. Min Act: -0.1700
Data Index: 410475 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.0705. Min Act: -0.1700
Data Index: 7555249 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.0080. Min Act: -0.1700
Data Index: 7902717 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.0080. Min Act: -0.1700
Data Index: 7676407 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.0080. Min Act: -0.1700
Data Index: 1752854 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0080. Min Range: -10.0080
Max Act: 9.0080. Min Act: -0.1700
Data Index: 5527528 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.9455. Min Act: -0.1700
Data Index: 8024119 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.8205. Min Act: -0.1700
Data Index: 6727428 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.8830. Min Act: -0.1700
Data Index: 386853 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.8830. Min Act: -0.1700
Data Index: 6382239 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.8205. Min Act: -0.1700
Data Index: 6124546 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.6955. Min Act: -0.1700
Data Index: 774768 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0080. Min Range: -10.0080
Max Act: 8.7580. Min Act: -0.1700
Data Index: 7466925 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19