Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0049. Min Range: -8.0049
Max Act: 8.0049. Min Act: -0.1700
Data Index: 2774298 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.7549. Min Act: -0.1700
Data Index: 607024 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.6299. Min Act: -0.1700
Data Index: 925680 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.5987. Min Act: -0.1700
Data Index: 3248675 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.3174. Min Act: -0.1700
Data Index: 1833664 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.3174. Min Act: -0.1700
Data Index: 7155508 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.3174. Min Act: -0.1700
Data Index: 6158122 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.3174. Min Act: -0.1700
Data Index: 3105528 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.2549. Min Act: -0.1700
Data Index: 6158121 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.2237. Min Act: -0.1700
Data Index: 1521217 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.1612. Min Act: -0.1700
Data Index: 6273871 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.1612. Min Act: -0.1700
Data Index: 399567 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.1299. Min Act: -0.1700
Data Index: 5304700 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.1299. Min Act: -0.1700
Data Index: 6495216 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.0987. Min Act: -0.1698
Data Index: 6459161 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.0362. Min Act: -0.1700
Data Index: 278738 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.0362. Min Act: -0.1700
Data Index: 674347 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.0049. Min Act: -0.1700
Data Index: 4895074 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.0049. Min Act: -0.1700
Data Index: 6972452 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0049. Min Range: -8.0049
Max Act: 7.0049. Min Act: -0.1700
Data Index: 5910592 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19