Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6007 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0209. Min Range: -7.0209
Max Act: 7.0209. Min Act: -0.1700
Data Index: 3472859 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.9584. Min Act: -0.1700
Data Index: 7491441 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.5834. Min Act: -0.1700
Data Index: 3334286 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.5522. Min Act: -0.1700
Data Index: 3809849 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.4897. Min Act: -0.1700
Data Index: 3170697 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.4272. Min Act: -0.1700
Data Index: 5176695 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3647. Min Act: -0.1700
Data Index: 7073016 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3647. Min Act: -0.1700
Data Index: 3621444 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1632600 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 4135678 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 2439019 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 681874 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 7184043 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 6945069 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 4590659 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3502908 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.3022. Min Act: -0.1700
Data Index: 6870498 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.2709. Min Act: -0.1700
Data Index: 2938961 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.2709. Min Act: -0.1700
Data Index: 6088404 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0209. Min Range: -7.0209
Max Act: 6.2709. Min Act: -0.1700
Data Index: 1573434 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19