Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0079. Min Range: -6.0079
Max Act: 6.0079. Min Act: -0.1700
Data Index: 4609326 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.8516. Min Act: -0.1700
Data Index: 81836 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.8204. Min Act: -0.1700
Data Index: 899107 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6954. Min Act: -0.1700
Data Index: 899103 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.7266. Min Act: -0.1700
Data Index: 2762622 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6954. Min Act: -0.1700
Data Index: 2505428 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6641. Min Act: -0.1700
Data Index: 1452993 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6329. Min Act: -0.1700
Data Index: 5778864 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6016. Min Act: -0.1700
Data Index: 5778860 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6016. Min Act: -0.1700
Data Index: 7711512 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.6016. Min Act: -0.1700
Data Index: 105829 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.5391. Min Act: -0.1700
Data Index: 5778857 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.5391. Min Act: -0.1700
Data Index: 5778861 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.5391. Min Act: -0.1700
Data Index: 2172655 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.5079. Min Act: -0.1700
Data Index: 4269604 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.5079. Min Act: -0.1700
Data Index: 2762621 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.4454. Min Act: -0.1700
Data Index: 3654219 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.4766. Min Act: -0.1700
Data Index: 7486048 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.4766. Min Act: -0.1700
Data Index: 5212772 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0079. Min Range: -6.0079
Max Act: 5.4454. Min Act: -0.1700
Data Index: 3037963 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19