Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 314 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.9213. Min Act: -0.1700
Data Index: 1476084 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.6401. Min Act: -0.1700
Data Index: 8648819 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.6713. Min Act: -0.1700
Data Index: 3446224 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.6088. Min Act: -0.1700
Data Index: 3649157 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.5463. Min Act: -0.1700
Data Index: 7907131 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4838. Min Act: -0.1700
Data Index: 7608627 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.5151. Min Act: -0.1700
Data Index: 6214841 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4526. Min Act: -0.1700
Data Index: 3625081 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4838. Min Act: -0.1700
Data Index: 8779853 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4526. Min Act: -0.1700
Data Index: 7570473 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4526. Min Act: -0.1700
Data Index: 4635131 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4213. Min Act: -0.1700
Data Index: 532044 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4213. Min Act: -0.1700
Data Index: 255982 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3588. Min Act: -0.1700
Data Index: 8134537 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3588. Min Act: -0.1700
Data Index: 2608298 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3588. Min Act: -0.1700
Data Index: 6147982 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3588. Min Act: -0.1700
Data Index: 5509290 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3276. Min Act: -0.1700
Data Index: 2757784 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3276. Min Act: -0.1700
Data Index: 2520448 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3276. Min Act: -0.1700
Data Index: 5650780 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19