Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1646 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.4393. Min Act: -0.1700
Data Index: 3469187 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.3455. Min Act: -0.1700
Data Index: 5645976 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.2830. Min Act: -0.1700
Data Index: 2746111 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.2518. Min Act: -0.1700
Data Index: 5106241 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.1893. Min Act: -0.1700
Data Index: 1724480 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.1580. Min Act: -0.1700
Data Index: 334532 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.1580. Min Act: -0.1700
Data Index: 6634890 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.0643. Min Act: -0.1700
Data Index: 5636805 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.0643. Min Act: -0.1700
Data Index: 7309215 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.0643. Min Act: -0.1700
Data Index: 22961 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.0330. Min Act: -0.1700
Data Index: 7839401 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.0018. Min Act: -0.1700
Data Index: 7185338 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4393. Min Range: -6.4393
Max Act: 6.0018. Min Act: -0.1700
Data Index: 6984607 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9393. Min Act: -0.1700
Data Index: 8693951 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9705. Min Act: -0.1700
Data Index: 6870715 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9705. Min Act: -0.1700
Data Index: 385355 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9080. Min Act: -0.1700
Data Index: 4092255 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9705. Min Act: -0.1700
Data Index: 7079376 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9393. Min Act: -0.1700
Data Index: 4245672 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4393. Min Range: -6.4393
Max Act: 5.9080. Min Act: -0.1700
Data Index: 1742739 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19