Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1662 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.4025. Min Act: -0.1700
Data Index: 6513653 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.3087. Min Act: -0.1700
Data Index: 5934113 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.2462. Min Act: -0.1700
Data Index: 3385545 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.1837. Min Act: -0.1700
Data Index: 5417259 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0900. Min Act: -0.1700
Data Index: 6110681 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 2523536 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0587. Min Act: -0.1700
Data Index: 6574863 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0587. Min Act: -0.1700
Data Index: 3633451 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 3757111 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 6581402 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 7902189 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 453448 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 884414 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 3578820 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 3855051 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 1110792 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 7854376 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 402492 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 5598423 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 4609123 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19