Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 228 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.4176. Min Act: -0.1695
Data Index: 2802846 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3824. Min Act: -0.1698
Data Index: 8627359 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3647. Min Act: -0.1700
Data Index: 5179772 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3736. Min Act: -0.1698
Data Index: 263433 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3647. Min Act: -0.1684
Data Index: 6811209 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3471. Min Act: -0.1700
Data Index: 4797236 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3559. Min Act: -0.1698
Data Index: 401731 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3559. Min Act: -0.1700
Data Index: 7840401 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3471. Min Act: -0.1700
Data Index: 1579643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3471. Min Act: -0.1700
Data Index: 6050138 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3471. Min Act: -0.1700
Data Index: 2992856 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3471. Min Act: -0.1700
Data Index: 7327576 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3207. Min Act: -0.1700
Data Index: 587414 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3207. Min Act: -0.1681
Data Index: 6736662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3207. Min Act: -0.1697
Data Index: 8384328 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3295. Min Act: -0.1700
Data Index: 6013239 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3030. Min Act: -0.1699
Data Index: 329718 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3295. Min Act: -0.1700
Data Index: 7202579 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3207. Min Act: -0.1696
Data Index: 2626228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4176. Min Range: -1.4176
Max Act: 1.3030. Min Act: -0.1700
Data Index: 3457020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19