Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.9939. Min Act: -0.1700
Data Index: 6076610 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.9939. Min Act: -0.1700
Data Index: 3197848 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.6189. Min Act: -0.1700
Data Index: 3776774 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.6189. Min Act: -0.1700
Data Index: 5025128 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.4939. Min Act: -0.1700
Data Index: 5770189 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.3689. Min Act: -0.1700
Data Index: 2642139 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.2439. Min Act: -0.1700
Data Index: 6043840 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.1814. Min Act: -0.1700
Data Index: 444207 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.1189. Min Act: -0.1700
Data Index: 2459454 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.1189. Min Act: -0.1700
Data Index: 2674010 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.1189. Min Act: -0.1700
Data Index: 6376042 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.1189. Min Act: -0.1700
Data Index: 6352245 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.0564. Min Act: -0.1700
Data Index: 7485622 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.0564. Min Act: -0.1700
Data Index: 3218754 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.0564. Min Act: -0.1700
Data Index: 362703 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9939. Min Range: -9.9939
Max Act: 9.0564. Min Act: -0.1700
Data Index: 6081098 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9939. Min Range: -9.9939
Max Act: 8.9939. Min Act: -0.1700
Data Index: 2291467 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9939. Min Range: -9.9939
Max Act: 8.8689. Min Act: -0.1700
Data Index: 560916 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9939. Min Range: -9.9939
Max Act: 8.8689. Min Act: -0.1700
Data Index: 2490950 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9939. Min Range: -9.9939
Max Act: 8.8689. Min Act: -0.1700
Data Index: 1019207 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19