Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.8393. Min Act: -0.1700
Data Index: 8786822 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.7768. Min Act: -0.1700
Data Index: 3679437 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.7143. Min Act: -0.1700
Data Index: 6896944 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6830. Min Act: -0.1700
Data Index: 8081869 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6830. Min Act: -0.1700
Data Index: 8152237 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6830. Min Act: -0.1700
Data Index: 6112668 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6830. Min Act: -0.1700
Data Index: 5108397 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6518. Min Act: -0.1700
Data Index: 6528244 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6518. Min Act: -0.1700
Data Index: 3253005 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6518. Min Act: -0.1700
Data Index: 4569743 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6830. Min Act: -0.1700
Data Index: 1538778 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.5893. Min Act: -0.1700
Data Index: 999561 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6205. Min Act: -0.1700
Data Index: 5936971 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6205. Min Act: -0.1700
Data Index: 448936 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.5893. Min Act: -0.1700
Data Index: 4536079 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6205. Min Act: -0.1700
Data Index: 1635493 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6205. Min Act: -0.1700
Data Index: 4413305 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.6205. Min Act: -0.1700
Data Index: 5376623 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.5580. Min Act: -0.1700
Data Index: 6744312 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8393. Min Range: -5.8393
Max Act: 5.5893. Min Act: -0.1700
Data Index: 8468217 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19