Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.4486. Min Act: -0.1700
Data Index: 3834471 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.4174. Min Act: -0.1700
Data Index: 8435136 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.3549. Min Act: -0.1700
Data Index: 6452218 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.3549. Min Act: -0.1700
Data Index: 5350630 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.3236. Min Act: -0.1700
Data Index: 247117 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6167910 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2611. Min Act: -0.1700
Data Index: 3913974 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2924. Min Act: -0.1700
Data Index: 2329835 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2924. Min Act: -0.1700
Data Index: 7255555 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2924. Min Act: -0.1700
Data Index: 5019773 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2611. Min Act: -0.1700
Data Index: 2450830 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2611. Min Act: -0.1700
Data Index: 8823370 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6958557 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2611. Min Act: -0.1700
Data Index: 3199055 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7546824 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1334947 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.1986. Min Act: -0.1700
Data Index: 5102512 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2299. Min Act: -0.1700
Data Index: 1770260 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7240174 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4486. Min Range: -5.4486
Max Act: 5.2299. Min Act: -0.1700
Data Index: 4808165 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19