Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.6443. Min Act: -0.1700
Data Index: 7682209 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.5818. Min Act: -0.1700
Data Index: 2196754 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.4880. Min Act: -0.1700
Data Index: 365506 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.4255. Min Act: -0.1700
Data Index: 3822949 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.3630. Min Act: -0.1700
Data Index: 966204 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.3318. Min Act: -0.1700
Data Index: 5526824 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.3005. Min Act: -0.1700
Data Index: 780543 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.3318. Min Act: -0.1700
Data Index: 5406145 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2692. Min Act: -0.1700
Data Index: 154470 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2380. Min Act: -0.1700
Data Index: 3829139 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2692. Min Act: -0.1700
Data Index: 4946474 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2380. Min Act: -0.1700
Data Index: 1807053 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2067. Min Act: -0.1700
Data Index: 1455509 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2380. Min Act: -0.1700
Data Index: 1740445 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2067. Min Act: -0.1700
Data Index: 1706522 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.2067. Min Act: -0.1700
Data Index: 2581286 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.1755. Min Act: -0.1700
Data Index: 7739904 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.1442. Min Act: -0.1700
Data Index: 4859992 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.1442. Min Act: -0.1700
Data Index: 1082944 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6443. Min Range: -4.6443
Max Act: 4.1442. Min Act: -0.1700
Data Index: 6343391 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19