Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.7864. Min Act: -0.1700
Data Index: 8447375 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.6301. Min Act: -0.1700
Data Index: 5424969 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.5051. Min Act: -0.1700
Data Index: 7605716 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3663353 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.3489. Min Act: -0.1700
Data Index: 1122047 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.3489. Min Act: -0.1700
Data Index: 6068371 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.3176. Min Act: -0.1700
Data Index: 2512418 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.3176. Min Act: -0.1700
Data Index: 5017517 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.2551. Min Act: -0.1700
Data Index: 7880931 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1614. Min Act: -0.1700
Data Index: 1243205 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1926. Min Act: -0.1700
Data Index: 5165346 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1614. Min Act: -0.1700
Data Index: 4540430 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1614. Min Act: -0.1700
Data Index: 4115234 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1301. Min Act: -0.1700
Data Index: 4772157 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1301. Min Act: -0.1700
Data Index: 4131840 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2055581 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1614. Min Act: -0.1700
Data Index: 1069704 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.1301. Min Act: -0.1700
Data Index: 3821906 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.0989. Min Act: -0.1700
Data Index: 952158 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7864. Min Range: -6.7864
Max Act: 6.0989. Min Act: -0.1700
Data Index: 3335492 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19