Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.5761. Min Act: -0.1700
Data Index: 1124112 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.4823. Min Act: -0.1700
Data Index: 4133365 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.4198. Min Act: -0.1700
Data Index: 1212417 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.3886. Min Act: -0.1700
Data Index: 4349050 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.3573. Min Act: -0.1700
Data Index: 5575631 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.2948. Min Act: -0.1700
Data Index: 8168643 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.2636. Min Act: -0.1700
Data Index: 3153801 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.2323. Min Act: -0.1700
Data Index: 7449819 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.2011. Min Act: -0.1700
Data Index: 1914942 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.1698. Min Act: -0.1700
Data Index: 5442683 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.1698. Min Act: -0.1700
Data Index: 4305514 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.1386. Min Act: -0.1700
Data Index: 4403951 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0761. Min Act: -0.1700
Data Index: 5583457 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0761. Min Act: -0.1700
Data Index: 817957 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0761. Min Act: -0.1700
Data Index: 1048959 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0448. Min Act: -0.1700
Data Index: 716403 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0448. Min Act: -0.1700
Data Index: 5442680 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3397759 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0136. Min Act: -0.1700
Data Index: 5255553 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5761. Min Range: -6.5761
Max Act: 6.0136. Min Act: -0.1700
Data Index: 392239 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19