Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 450 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.9885. Min Act: -0.1700
Data Index: 5389464 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.8635. Min Act: -0.1700
Data Index: 1232822 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.8323. Min Act: -0.1700
Data Index: 5642164 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.8323. Min Act: -0.1700
Data Index: 5571342 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.8323. Min Act: -0.1700
Data Index: 4906636 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.8010. Min Act: -0.1699
Data Index: 2396948 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.8010. Min Act: -0.1700
Data Index: 7393020 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7698. Min Act: -0.1700
Data Index: 2851345 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7698. Min Act: -0.1700
Data Index: 1872304 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7385. Min Act: -0.1700
Data Index: 4673654 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7698. Min Act: -0.1692
Data Index: 3906768 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7385. Min Act: -0.1700
Data Index: 1179469 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7385. Min Act: -0.1699
Data Index: 4649368 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7073. Min Act: -0.1700
Data Index: 4806630 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7073. Min Act: -0.1700
Data Index: 8553613 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7073. Min Act: -0.1700
Data Index: 5727403 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7073. Min Act: -0.1700
Data Index: 499104 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.7073. Min Act: -0.1700
Data Index: 1715775 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.6760. Min Act: -0.1700
Data Index: 2622768 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9885. Min Range: -5.9885
Max Act: 5.6760. Min Act: -0.1700
Data Index: 5390102 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19