Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 365 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.6003. Min Act: -0.1700
Data Index: 5410335 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.5378. Min Act: -0.1700
Data Index: 6277232 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.4753. Min Act: -0.1700
Data Index: 3074327 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.4128. Min Act: -0.1700
Data Index: 3309298 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.4128. Min Act: -0.1700
Data Index: 1734402 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3816. Min Act: -0.1700
Data Index: 185986 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3816. Min Act: -0.1700
Data Index: 6480563 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3503. Min Act: -0.1700
Data Index: 2947023 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3503. Min Act: -0.1700
Data Index: 2747124 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3503. Min Act: -0.1700
Data Index: 4293868 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3191. Min Act: -0.1700
Data Index: 7429593 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.3191. Min Act: -0.1700
Data Index: 1595462 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 5635852 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 2732923 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 751293 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 1081978 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 8784512 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 1651149 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2566. Min Act: -0.1700
Data Index: 3885515 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6003. Min Range: -4.6003
Max Act: 4.2878. Min Act: -0.1700
Data Index: 3309286 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19