Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.2683. Min Act: -0.1700
Data Index: 6127044 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.2369. Min Act: -0.1700
Data Index: 6921270 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.1582. Min Act: -0.1700
Data Index: 1768260 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.1582. Min Act: -0.1700
Data Index: 4519836 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0952. Min Act: -0.1700
Data Index: 7155657 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0794. Min Act: -0.1700
Data Index: 6908075 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.1110. Min Act: -0.1700
Data Index: 590749 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0952. Min Act: -0.1700
Data Index: 5403432 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0637. Min Act: -0.1700
Data Index: 8677280 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0321. Min Act: -0.1700
Data Index: 917423 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0479. Min Act: -0.1700
Data Index: 5785277 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0321. Min Act: -0.1700
Data Index: 6157929 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0321. Min Act: -0.1700
Data Index: 1232170 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0005. Min Act: -0.1700
Data Index: 413875 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0163. Min Act: -0.1700
Data Index: 5645527 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0005. Min Act: -0.1700
Data Index: 8710945 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0163. Min Act: -0.1700
Data Index: 2387352 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2683. Min Range: -3.2683
Max Act: 2.9689. Min Act: -0.1700
Data Index: 1436868 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2683. Min Range: -3.2683
Max Act: 3.0005. Min Act: -0.1700
Data Index: 6916721 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2683. Min Range: -3.2683
Max Act: 2.9689. Min Act: -0.1700
Data Index: 6862661 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19