Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3854 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.5550. Min Act: -0.1700
Data Index: 7668825 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4925. Min Act: -0.1700
Data Index: 5171930 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4925. Min Act: -0.1700
Data Index: 4207456 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4613. Min Act: -0.1700
Data Index: 7412026 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4613. Min Act: -0.1700
Data Index: 5660724 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4300. Min Act: -0.1700
Data Index: 1360112 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4300. Min Act: -0.1700
Data Index: 7694877 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3988. Min Act: -0.1700
Data Index: 2897671 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3675. Min Act: -0.1700
Data Index: 6556840 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3675. Min Act: -0.1700
Data Index: 347901 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3093492 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 4566589 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 1295497 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3525539 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 719987 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 8493694 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 6170458 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3050. Min Act: -0.1700
Data Index: 3309924 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3050. Min Act: -0.1700
Data Index: 3256126 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2737. Min Act: -0.1700
Data Index: 8781418 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19