Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.9042. Min Act: -0.1700
Data Index: 6518031 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.7792. Min Act: -0.1700
Data Index: 910959 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.7480. Min Act: -0.1700
Data Index: 1146190 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6855. Min Act: -0.1700
Data Index: 2862179 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6542. Min Act: -0.1700
Data Index: 3925774 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6855. Min Act: -0.1700
Data Index: 5097573 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6542. Min Act: -0.1700
Data Index: 4677463 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6230. Min Act: -0.1700
Data Index: 2726256 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6230. Min Act: -0.1700
Data Index: 734706 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5917. Min Act: -0.1700
Data Index: 8416509 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.6230. Min Act: -0.1700
Data Index: 1960084 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5605. Min Act: -0.1700
Data Index: 238962 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5917. Min Act: -0.1700
Data Index: 3077257 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5917. Min Act: -0.1700
Data Index: 5400659 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5605. Min Act: -0.1700
Data Index: 5415106 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5292. Min Act: -0.1700
Data Index: 1002555 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5605. Min Act: -0.1700
Data Index: 2173654 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5605. Min Act: -0.1700
Data Index: 1333827 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5292. Min Act: -0.1700
Data Index: 538676 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9042. Min Range: -5.9042
Max Act: 5.5605. Min Act: -0.1700
Data Index: 5599309 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19