Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4611 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.7471. Min Act: -0.1700
Data Index: 1669829 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.5908. Min Act: -0.1700
Data Index: 1108903 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.4971. Min Act: -0.1700
Data Index: 2972017 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.4033. Min Act: -0.1700
Data Index: 25625 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.3721. Min Act: -0.1700
Data Index: 1044275 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.3721. Min Act: -0.1700
Data Index: 8531365 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.3408. Min Act: -0.1700
Data Index: 3486456 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.3408. Min Act: -0.1700
Data Index: 2467574 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.3096. Min Act: -0.1700
Data Index: 3856879 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.3408. Min Act: -0.1700
Data Index: 8216938 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.2783. Min Act: -0.1700
Data Index: 937821 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.2158. Min Act: -0.1700
Data Index: 5369496 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.1846. Min Act: -0.1700
Data Index: 3703262 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.1533. Min Act: -0.1700
Data Index: 3189409 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.0908. Min Act: -0.1700
Data Index: 8568457 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.1221. Min Act: -0.1700
Data Index: 665574 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.0908. Min Act: -0.1700
Data Index: 4396073 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7471. Min Range: -6.7471
Max Act: 6.0283. Min Act: -0.1700
Data Index: 8228353 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7471. Min Range: -6.7471
Max Act: 5.9971. Min Act: -0.1700
Data Index: 7514962 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7471. Min Range: -6.7471
Max Act: 5.9971. Min Act: -0.1700
Data Index: 410682 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19