Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5477 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.4976. Min Act: -0.1700
Data Index: 5368063 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.4351. Min Act: -0.1700
Data Index: 491709 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 5168144 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 4578216 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 1079838 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 5665816 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.3414. Min Act: -0.1700
Data Index: 2038623 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 3649941 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.2789. Min Act: -0.1700
Data Index: 8329867 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.2789. Min Act: -0.1700
Data Index: 7371040 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.2164. Min Act: -0.1700
Data Index: 391172 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.2164. Min Act: -0.1700
Data Index: 7268171 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.1539. Min Act: -0.1700
Data Index: 5120753 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.1539. Min Act: -0.1700
Data Index: 7790124 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.1226. Min Act: -0.1700
Data Index: 364859 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.1226. Min Act: -0.1700
Data Index: 3963276 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.1226. Min Act: -0.1700
Data Index: 3880913 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.1226. Min Act: -0.1700
Data Index: 8767229 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.0914. Min Act: -0.1700
Data Index: 4730650 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4976. Min Range: -5.4976
Max Act: 5.0601. Min Act: -0.1700
Data Index: 8095470 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19