Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.9205. Min Act: -0.1700
Data Index: 8053887 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.6705. Min Act: -0.1700
Data Index: 721103 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.6705. Min Act: -0.1700
Data Index: 6974357 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 6922430 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 1377336 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.5455. Min Act: -0.1700
Data Index: 2793373 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.4830. Min Act: -0.1700
Data Index: 6366239 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.4205. Min Act: -0.1700
Data Index: 7862122 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.3580. Min Act: -0.1700
Data Index: 5660431 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.2955. Min Act: -0.1700
Data Index: 2369218 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.2330. Min Act: -0.1700
Data Index: 582836 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.2955. Min Act: -0.1700
Data Index: 549352 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.2330. Min Act: -0.1700
Data Index: 6475049 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1705. Min Act: -0.1700
Data Index: 376247 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1705. Min Act: -0.1700
Data Index: 4910611 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1080. Min Act: -0.1700
Data Index: 1909325 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1080. Min Act: -0.1700
Data Index: 989110 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1080. Min Act: -0.1700
Data Index: 550751 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1080. Min Act: -0.1700
Data Index: 2363665 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9205. Min Range: -8.9205
Max Act: 8.1080. Min Act: -0.1700
Data Index: 73168 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19