Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.4152. Min Act: -0.1700
Data Index: 3716023 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.3214. Min Act: -0.1700
Data Index: 4474793 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.2902. Min Act: -0.1700
Data Index: 2091405 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.2589. Min Act: -0.1700
Data Index: 2973675 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.2277. Min Act: -0.1700
Data Index: 4286432 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.2277. Min Act: -0.1700
Data Index: 1432031 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.1652. Min Act: -0.1700
Data Index: 5072525 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.1652. Min Act: -0.1700
Data Index: 4464635 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.1339. Min Act: -0.1700
Data Index: 7459550 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.1027. Min Act: -0.1700
Data Index: 2072621 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.1027. Min Act: -0.1700
Data Index: 6709693 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.1027. Min Act: -0.1700
Data Index: 3862312 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0714. Min Act: -0.1700
Data Index: 6835925 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0714. Min Act: -0.1700
Data Index: 7753495 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0402. Min Act: -0.1700
Data Index: 946292 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0402. Min Act: -0.1700
Data Index: 121415 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0089. Min Act: -0.1700
Data Index: 1432027 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3648497 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4152. Min Range: -5.4152
Max Act: 5.0402. Min Act: -0.1700
Data Index: 7437264 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4152. Min Range: -5.4152
Max Act: 4.9777. Min Act: -0.1700
Data Index: 3753756 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19