Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.6971. Min Act: -0.1700
Data Index: 7125015 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.6658. Min Act: -0.1700
Data Index: 3478381 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.6033. Min Act: -0.1700
Data Index: 4524458 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.6346. Min Act: -0.1700
Data Index: 4574605 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.6033. Min Act: -0.1700
Data Index: 3171626 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5721. Min Act: -0.1700
Data Index: 3445664 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.6033. Min Act: -0.1700
Data Index: 8273231 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5096. Min Act: -0.1700
Data Index: 1653959 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5408. Min Act: -0.1700
Data Index: 4766306 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5408. Min Act: -0.1700
Data Index: 7529554 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5408. Min Act: -0.1700
Data Index: 6409708 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.4783. Min Act: -0.1700
Data Index: 4731328 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.4783. Min Act: -0.1700
Data Index: 22434 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5096. Min Act: -0.1700
Data Index: 1752458 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5096. Min Act: -0.1700
Data Index: 6812520 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5096. Min Act: -0.1700
Data Index: 6984914 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5096. Min Act: -0.1700
Data Index: 159575 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.4783. Min Act: -0.1700
Data Index: 4116813 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.5096. Min Act: -0.1700
Data Index: 4152623 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6971. Min Range: -4.6971
Max Act: 4.4783. Min Act: -0.1700
Data Index: 5003917 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19