Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4852 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.7864. Min Act: -0.1700
Data Index: 5856221 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.7864. Min Act: -0.1700
Data Index: 3290307 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.7239. Min Act: -0.1700
Data Index: 3509683 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.6614. Min Act: -0.1700
Data Index: 1461913 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.6302. Min Act: -0.1700
Data Index: 1473109 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.5364. Min Act: -0.1697
Data Index: 5786744 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.5052. Min Act: -0.1700
Data Index: 1363847 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4739. Min Act: -0.1697
Data Index: 8317223 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4739. Min Act: -0.1700
Data Index: 761957 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4739. Min Act: -0.1698
Data Index: 2126468 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1700
Data Index: 689826 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4739. Min Act: -0.1699
Data Index: 5458927 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4427. Min Act: -0.1700
Data Index: 4355810 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1700
Data Index: 3916828 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1700
Data Index: 1221357 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1699
Data Index: 3169012 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1700
Data Index: 4785206 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1697
Data Index: 3270051 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1700
Data Index: 3106431 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7864. Min Range: -4.7864
Max Act: 4.4114. Min Act: -0.1700
Data Index: 6063356 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19