Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.8033. Min Act: -0.1700
Data Index: 5316515 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.7721. Min Act: -0.1700
Data Index: 2856468 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.6158. Min Act: -0.1700
Data Index: 7712351 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5846. Min Act: -0.1700
Data Index: 4355590 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5533. Min Act: -0.1700
Data Index: 4432148 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5533. Min Act: -0.1700
Data Index: 3688983 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5221. Min Act: -0.1700
Data Index: 5768618 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4908. Min Act: -0.1700
Data Index: 6606746 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5221. Min Act: -0.1700
Data Index: 6226089 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 1823902 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 892015 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 5507596 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 3291930 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3971. Min Act: -0.1700
Data Index: 7324296 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3971. Min Act: -0.1700
Data Index: 4015297 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 6957123 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3658. Min Act: -0.1700
Data Index: 5850828 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3658. Min Act: -0.1700
Data Index: 5865004 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3658. Min Act: -0.1700
Data Index: 4486989 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3346. Min Act: -0.1700
Data Index: 2797427 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19