Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.5175. Min Act: -0.1700
Data Index: 3836755 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.3925. Min Act: -0.1700
Data Index: 8253652 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.3612. Min Act: -0.1700
Data Index: 4188649 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.3300. Min Act: -0.1700
Data Index: 2711052 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.2987. Min Act: -0.1700
Data Index: 6261041 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.2362. Min Act: -0.1700
Data Index: 3406945 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.2050. Min Act: -0.1700
Data Index: 8428508 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1737. Min Act: -0.1700
Data Index: 1419873 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1737. Min Act: -0.1700
Data Index: 668094 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1737. Min Act: -0.1700
Data Index: 3201623 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1425. Min Act: -0.1700
Data Index: 1450419 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1425. Min Act: -0.1700
Data Index: 5826997 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1425. Min Act: -0.1700
Data Index: 4631428 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1112. Min Act: -0.1700
Data Index: 6673915 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1112. Min Act: -0.1700
Data Index: 5096988 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1112. Min Act: -0.1700
Data Index: 3764907 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1112. Min Act: -0.1700
Data Index: 7956824 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1425. Min Act: -0.1700
Data Index: 6276870 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1112. Min Act: -0.1700
Data Index: 2573788 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5175. Min Range: -5.5175
Max Act: 5.1112. Min Act: -0.1700
Data Index: 4878475 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19