Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0239. Min Range: -6.0239
Max Act: 6.0239. Min Act: -0.1700
Data Index: 8243224 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.8364. Min Act: -0.1700
Data Index: 4985187 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.8051. Min Act: -0.1700
Data Index: 8046376 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.8364. Min Act: -0.1700
Data Index: 4697067 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.7114. Min Act: -0.1700
Data Index: 3663912 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.6489. Min Act: -0.1700
Data Index: 759503 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.6176. Min Act: -0.1700
Data Index: 1125042 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5864. Min Act: -0.1700
Data Index: 5440121 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5864. Min Act: -0.1700
Data Index: 4054340 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5551. Min Act: -0.1700
Data Index: 2014555 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.6176. Min Act: -0.1700
Data Index: 6529145 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5864. Min Act: -0.1700
Data Index: 6604361 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 8346038 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4495169 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 2537725 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 2421790 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5882718 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4276343 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5042136 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0239. Min Range: -6.0239
Max Act: 5.5551. Min Act: -0.1700
Data Index: 7901712 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19