Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3956. Min Act: -0.1700
Data Index: 2470024 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3956. Min Act: -0.1700
Data Index: 306120 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3956. Min Act: -0.1700
Data Index: 3180715 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3642. Min Act: -0.1700
Data Index: 6762590 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3486. Min Act: -0.1700
Data Index: 1950254 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3486. Min Act: -0.1700
Data Index: 5503781 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3329. Min Act: -0.1700
Data Index: 3227684 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3329. Min Act: -0.1700
Data Index: 57359 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3329. Min Act: -0.1700
Data Index: 2498519 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3172. Min Act: -0.1700
Data Index: 7506062 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3172. Min Act: -0.1700
Data Index: 2021585 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3015. Min Act: -0.1700
Data Index: 2097737 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.3015. Min Act: -0.1700
Data Index: 2731111 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2858. Min Act: -0.1700
Data Index: 7964592 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2858. Min Act: -0.1700
Data Index: 8730770 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2701. Min Act: -0.1700
Data Index: 1090245 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2858. Min Act: -0.1700
Data Index: 6134367 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2701. Min Act: -0.1700
Data Index: 687315 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2544. Min Act: -0.1700
Data Index: 7461080 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3956. Min Range: -3.3956
Max Act: 3.2386. Min Act: -0.1700
Data Index: 4359429 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19