Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4392. Min Range: -7.4392
Max Act: 7.4392. Min Act: -0.1700
Data Index: 1604466 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4392. Min Range: -7.4392
Max Act: 7.2517. Min Act: -0.1700
Data Index: 8486624 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4392. Min Range: -7.4392
Max Act: 7.0329. Min Act: -0.1700
Data Index: 3248585 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4392. Min Range: -7.4392
Max Act: 7.0017. Min Act: -0.1700
Data Index: 6061059 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.9079. Min Act: -0.1700
Data Index: 8415783 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.8767. Min Act: -0.1700
Data Index: 8175639 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.8142. Min Act: -0.1700
Data Index: 5095541 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.8142. Min Act: -0.1700
Data Index: 7164529 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.8142. Min Act: -0.1700
Data Index: 5080551 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.7829. Min Act: -0.1700
Data Index: 3588154 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.7829. Min Act: -0.1700
Data Index: 4921704 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.7204. Min Act: -0.1700
Data Index: 6040148 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.7204. Min Act: -0.1700
Data Index: 1460543 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6892. Min Act: -0.1700
Data Index: 5945777 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6892. Min Act: -0.1700
Data Index: 8450123 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6579. Min Act: -0.1700
Data Index: 7380250 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6579. Min Act: -0.1700
Data Index: 1273808 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6892. Min Act: -0.1700
Data Index: 6128573 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6892. Min Act: -0.1700
Data Index: 790400 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4392. Min Range: -7.4392
Max Act: 6.6579. Min Act: -0.1700
Data Index: 7278969 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19