Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.3708. Min Act: -0.1700
Data Index: 3277552 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.3708. Min Act: -0.1700
Data Index: 783774 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.3083. Min Act: -0.1700
Data Index: 6358111 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.2146. Min Act: -0.1700
Data Index: 4269355 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1833. Min Act: -0.1700
Data Index: 4672445 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1833. Min Act: -0.1700
Data Index: 3574357 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1208. Min Act: -0.1700
Data Index: 8461673 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1208. Min Act: -0.1700
Data Index: 1756565 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1208. Min Act: -0.1700
Data Index: 532847 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 8734629 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 2749839 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 4810836 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 6516564 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 8238522 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 4384604 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 3150921 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0583. Min Act: -0.1700
Data Index: 1327149 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0583. Min Act: -0.1700
Data Index: 1339495 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0583. Min Act: -0.1700
Data Index: 729820 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0583. Min Act: -0.1700
Data Index: 6561694 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19