Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3259 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2425. Min Range: -6.2425
Max Act: 6.2425. Min Act: -0.1700
Data Index: 57560 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2425. Min Range: -6.2425
Max Act: 6.1487. Min Act: -0.1700
Data Index: 1440060 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2425. Min Range: -6.2425
Max Act: 6.0862. Min Act: -0.1700
Data Index: 2396719 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2425. Min Range: -6.2425
Max Act: 6.0237. Min Act: -0.1700
Data Index: 2400348 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9925. Min Act: -0.1700
Data Index: 1179646 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9300. Min Act: -0.1700
Data Index: 8678500 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9300. Min Act: -0.1700
Data Index: 7385284 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9300. Min Act: -0.1700
Data Index: 7021709 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9300. Min Act: -0.1700
Data Index: 3236932 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9300. Min Act: -0.1700
Data Index: 147002 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8675. Min Act: -0.1700
Data Index: 6366873 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8987. Min Act: -0.1700
Data Index: 403535 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8987. Min Act: -0.1700
Data Index: 3885885 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8987. Min Act: -0.1700
Data Index: 6217791 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8987. Min Act: -0.1700
Data Index: 132983 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.9300. Min Act: -0.1700
Data Index: 530389 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8362. Min Act: -0.1700
Data Index: 5178963 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8675. Min Act: -0.1700
Data Index: 2997549 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8362. Min Act: -0.1700
Data Index: 2246520 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8362. Min Act: -0.1700
Data Index: 182952 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19