Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.3470. Min Act: -0.1700
Data Index: 2264100 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.1900. Min Act: -0.1700
Data Index: 8067043 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0797. Min Act: -0.1700
Data Index: 165597 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0797. Min Act: -0.1700
Data Index: 3414760 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0008. Min Act: -0.1700
Data Index: 2252573 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0008. Min Act: -0.1700
Data Index: 2655036 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0324. Min Act: -0.1700
Data Index: 8014112 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0324. Min Act: -0.1700
Data Index: 1855584 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0324. Min Act: -0.1700
Data Index: 444169 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0324. Min Act: -0.1700
Data Index: 1947043 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0324. Min Act: -0.1700
Data Index: 5678101 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0008. Min Act: -0.1700
Data Index: 5148222 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0008. Min Act: -0.1700
Data Index: 2182936 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3470. Min Range: -3.3470
Max Act: 3.0008. Min Act: -0.1700
Data Index: 4164591 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3470. Min Range: -3.3470
Max Act: 2.9850. Min Act: -0.1700
Data Index: 7384298 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3470. Min Range: -3.3470
Max Act: 2.9692. Min Act: -0.1700
Data Index: 4382676 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3470. Min Range: -3.3470
Max Act: 2.9692. Min Act: -0.1700
Data Index: 81289 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3470. Min Range: -3.3470
Max Act: 2.9375. Min Act: -0.1700
Data Index: 1280379 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3470. Min Range: -3.3470
Max Act: 2.9692. Min Act: -0.1700
Data Index: 1222681 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3470. Min Range: -3.3470
Max Act: 2.9533. Min Act: -0.1700
Data Index: 2176995 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19