Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.9113. Min Act: -0.1700
Data Index: 1537023 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.8488. Min Act: -0.1700
Data Index: 3429649 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.5676. Min Act: -0.1700
Data Index: 522982 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.4738. Min Act: -0.1700
Data Index: 8789159 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8521530 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.4426. Min Act: -0.1700
Data Index: 4234812 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8117538 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.4113. Min Act: -0.1700
Data Index: 3604952 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.3801. Min Act: -0.1700
Data Index: 7407472 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.4113. Min Act: -0.1700
Data Index: 8533778 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.3801. Min Act: -0.1700
Data Index: 499282 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.3488. Min Act: -0.1700
Data Index: 2004163 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.3176. Min Act: -0.1700
Data Index: 6621016 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2863. Min Act: -0.1700
Data Index: 3526688 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2551. Min Act: -0.1700
Data Index: 8653819 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2863. Min Act: -0.1700
Data Index: 6749017 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2238. Min Act: -0.1700
Data Index: 7173969 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2551. Min Act: -0.1700
Data Index: 4437837 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2238. Min Act: -0.1700
Data Index: 7489056 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9113. Min Range: -6.9113
Max Act: 6.2238. Min Act: -0.1700
Data Index: 514171 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19