Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0462. Min Range: -7.0462
Max Act: 7.0462. Min Act: -0.1700
Data Index: 4746250 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.8587. Min Act: -0.1700
Data Index: 2675664 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.7337. Min Act: -0.1700
Data Index: 2524659 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.5774. Min Act: -0.1700
Data Index: 7526493 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.5149. Min Act: -0.1700
Data Index: 3744637 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.4212. Min Act: -0.1700
Data Index: 8284953 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.4212. Min Act: -0.1700
Data Index: 6519007 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.3899. Min Act: -0.1700
Data Index: 785823 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.3274. Min Act: -0.1700
Data Index: 2545908 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.3274. Min Act: -0.1700
Data Index: 6213707 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2962. Min Act: -0.1700
Data Index: 5680380 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2649. Min Act: -0.1700
Data Index: 4828567 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2337. Min Act: -0.1700
Data Index: 3066827 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2337. Min Act: -0.1700
Data Index: 7655976 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2337. Min Act: -0.1700
Data Index: 5934644 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2024. Min Act: -0.1700
Data Index: 3751708 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.2024. Min Act: -0.1700
Data Index: 7962810 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.1712. Min Act: -0.1700
Data Index: 6962886 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.1399. Min Act: -0.1700
Data Index: 7701213 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0462. Min Range: -7.0462
Max Act: 6.1399. Min Act: -0.1700
Data Index: 4286401 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19