Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.9817. Min Act: -0.1700
Data Index: 1740662 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.9817. Min Act: -0.1700
Data Index: 5255046 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.8880. Min Act: -0.1700
Data Index: 5122034 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.7630. Min Act: -0.1700
Data Index: 5196144 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.7317. Min Act: -0.1700
Data Index: 5909813 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.7630. Min Act: -0.1700
Data Index: 8355308 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.6380. Min Act: -0.1700
Data Index: 4190028 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.6380. Min Act: -0.1700
Data Index: 5814965 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.6380. Min Act: -0.1700
Data Index: 2806243 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.6380. Min Act: -0.1700
Data Index: 1061185 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.6380. Min Act: -0.1700
Data Index: 7154222 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5755. Min Act: -0.1700
Data Index: 4841702 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5755. Min Act: -0.1700
Data Index: 6554393 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5442. Min Act: -0.1700
Data Index: 983877 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5442. Min Act: -0.1700
Data Index: 8681201 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5442. Min Act: -0.1700
Data Index: 1440905 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5442. Min Act: -0.1700
Data Index: 3233080 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5130. Min Act: -0.1700
Data Index: 7641183 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5130. Min Act: -0.1700
Data Index: 7791363 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9817. Min Range: -4.9817
Max Act: 4.5130. Min Act: -0.1700
Data Index: 308408 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19