Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1127 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.3524. Min Act: -0.1700
Data Index: 3884102 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.3054. Min Act: -0.1700
Data Index: 5662573 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.2897. Min Act: -0.1700
Data Index: 3268200 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.2583. Min Act: -0.1700
Data Index: 7950767 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.2425. Min Act: -0.1700
Data Index: 731617 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.2268. Min Act: -0.1700
Data Index: 2408437 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.2268. Min Act: -0.1700
Data Index: 3570670 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1954. Min Act: -0.1700
Data Index: 545246 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1482. Min Act: -0.1700
Data Index: 458531 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1482. Min Act: -0.1700
Data Index: 5036925 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1797. Min Act: -0.1700
Data Index: 8286615 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1639. Min Act: -0.1700
Data Index: 6403649 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1639. Min Act: -0.1700
Data Index: 1721544 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1639. Min Act: -0.1700
Data Index: 3358592 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1482. Min Act: -0.1700
Data Index: 6470687 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1324. Min Act: -0.1700
Data Index: 985967 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1324. Min Act: -0.1700
Data Index: 6959428 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1324. Min Act: -0.1700
Data Index: 4174150 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1167. Min Act: -0.1700
Data Index: 1537033 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3524. Min Range: -3.3524
Max Act: 3.1324. Min Act: -0.1700
Data Index: 3278379 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19