Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.5754. Min Act: -0.1700
Data Index: 7537110 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4816. Min Act: -0.1700
Data Index: 6679449 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4191. Min Act: -0.1700
Data Index: 3873979 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4504. Min Act: -0.1700
Data Index: 991732 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4191. Min Act: -0.1700
Data Index: 1149718 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3566. Min Act: -0.1700
Data Index: 7393134 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3566. Min Act: -0.1700
Data Index: 77355 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3566. Min Act: -0.1700
Data Index: 3141164 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 2997231 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 1215968 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 4493657 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 1860530 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3566. Min Act: -0.1700
Data Index: 2333850 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 6964342 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 4378294 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 3835257 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 5952325 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 3586782 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 4943313 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 187523 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19