Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.9709. Min Act: -0.1700
Data Index: 904589 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.9709. Min Act: -0.1700
Data Index: 7438714 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.9084. Min Act: -0.1700
Data Index: 6422337 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.8771. Min Act: -0.1700
Data Index: 2711898 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.8771. Min Act: -0.1700
Data Index: 388547 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.8146. Min Act: -0.1700
Data Index: 1598964 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.8146. Min Act: -0.1700
Data Index: 3187331 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.7521. Min Act: -0.1700
Data Index: 8644562 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.6896. Min Act: -0.1700
Data Index: 8752500 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.7209. Min Act: -0.1700
Data Index: 725307 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.6584. Min Act: -0.1700
Data Index: 4742983 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.6896. Min Act: -0.1700
Data Index: 1690886 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5959. Min Act: -0.1700
Data Index: 8795482 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.6271. Min Act: -0.1700
Data Index: 6891084 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5959. Min Act: -0.1700
Data Index: 442319 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5646. Min Act: -0.1700
Data Index: 7420038 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5334. Min Act: -0.1700
Data Index: 2613313 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5021. Min Act: -0.1700
Data Index: 8499528 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5334. Min Act: -0.1700
Data Index: 5784360 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9709. Min Range: -6.9709
Max Act: 6.5021. Min Act: -0.1700
Data Index: 2223980 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19