Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 494 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.3697. Min Act: -0.1700
Data Index: 4269241 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.8697. Min Act: -0.1700
Data Index: 5508209 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.8385. Min Act: -0.1700
Data Index: 4840132 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.8072. Min Act: -0.1700
Data Index: 7544921 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.7447. Min Act: -0.1700
Data Index: 7482491 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.6510. Min Act: -0.1700
Data Index: 1754095 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.6510. Min Act: -0.1700
Data Index: 715896 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.6822. Min Act: -0.1700
Data Index: 3786249 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.6197. Min Act: -0.1700
Data Index: 1581083 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 4095910 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.4947. Min Act: -0.1700
Data Index: 3786251 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4557479 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.4322. Min Act: -0.1700
Data Index: 7508904 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.3697. Min Act: -0.1700
Data Index: 3852405 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.4010. Min Act: -0.1700
Data Index: 6730949 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.4010. Min Act: -0.1700
Data Index: 99536 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.4010. Min Act: -0.1700
Data Index: 6492114 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.3697. Min Act: -0.1700
Data Index: 2593920 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.3385. Min Act: -0.1700
Data Index: 252680 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.3385. Min Act: -0.1700
Data Index: 4702442 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19