Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2586. Min Range: -6.2586
Max Act: 6.2586. Min Act: -0.1700
Data Index: 3808693 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2586. Min Range: -6.2586
Max Act: 6.1961. Min Act: -0.1700
Data Index: 2405654 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2586. Min Range: -6.2586
Max Act: 6.1961. Min Act: -0.1700
Data Index: 5604005 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2586. Min Range: -6.2586
Max Act: 6.0086. Min Act: -0.1700
Data Index: 227833 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9773. Min Act: -0.1700
Data Index: 538622 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2586. Min Range: -6.2586
Max Act: 6.0086. Min Act: -0.1700
Data Index: 1808110 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9461. Min Act: -0.1700
Data Index: 5307386 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9148. Min Act: -0.1700
Data Index: 8231605 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9461. Min Act: -0.1700
Data Index: 339505 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.8836. Min Act: -0.1700
Data Index: 7246331 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9148. Min Act: -0.1700
Data Index: 6102794 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9148. Min Act: -0.1700
Data Index: 2401126 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.8836. Min Act: -0.1700
Data Index: 3764429 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.9148. Min Act: -0.1700
Data Index: 2160468 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.8523. Min Act: -0.1700
Data Index: 7923946 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.8211. Min Act: -0.1700
Data Index: 8510531 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.8211. Min Act: -0.1700
Data Index: 7269327 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.7898. Min Act: -0.1700
Data Index: 4479909 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.7273. Min Act: -0.1700
Data Index: 2554545 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2586. Min Range: -6.2586
Max Act: 5.7898. Min Act: -0.1700
Data Index: 8379958 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19