Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0254. Min Range: -5.0254
Max Act: 5.0254. Min Act: -0.1700
Data Index: 5621936 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.9941. Min Act: -0.1700
Data Index: 6276626 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.9941. Min Act: -0.1700
Data Index: 87281 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.9316. Min Act: -0.1700
Data Index: 2874830 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.9629. Min Act: -0.1700
Data Index: 8667604 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8691. Min Act: -0.1700
Data Index: 5285006 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8691. Min Act: -0.1700
Data Index: 1430120 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8379. Min Act: -0.1700
Data Index: 551509 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8691. Min Act: -0.1700
Data Index: 736256 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8066. Min Act: -0.1700
Data Index: 1259456 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8379. Min Act: -0.1700
Data Index: 6076711 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.7754. Min Act: -0.1700
Data Index: 6629466 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8066. Min Act: -0.1700
Data Index: 685606 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8066. Min Act: -0.1700
Data Index: 6637524 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.7754. Min Act: -0.1700
Data Index: 8485170 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.7754. Min Act: -0.1700
Data Index: 343820 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8066. Min Act: -0.1700
Data Index: 1771680 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.8379. Min Act: -0.1700
Data Index: 4357986 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.7129. Min Act: -0.1700
Data Index: 6805766 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0254. Min Range: -5.0254
Max Act: 4.7754. Min Act: -0.1700
Data Index: 7580611 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19