Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.8453. Min Act: -0.1700
Data Index: 5377643 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.8140. Min Act: -0.1700
Data Index: 4815311 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.7515. Min Act: -0.1700
Data Index: 3000834 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.4078. Min Act: -0.1700
Data Index: 7178803 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.3453. Min Act: -0.1700
Data Index: 8005440 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.3140. Min Act: -0.1700
Data Index: 1485187 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.2828. Min Act: -0.1700
Data Index: 6430048 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.2515. Min Act: -0.1700
Data Index: 395910 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.1890. Min Act: -0.1700
Data Index: 3606006 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.1578. Min Act: -0.1700
Data Index: 7918491 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.1265. Min Act: -0.1700
Data Index: 4702523 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.1578. Min Act: -0.1700
Data Index: 912352 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.1265. Min Act: -0.1700
Data Index: 798491 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.0640. Min Act: -0.1700
Data Index: 7970162 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.0328. Min Act: -0.1700
Data Index: 7878975 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.0640. Min Act: -0.1700
Data Index: 8707554 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.0640. Min Act: -0.1700
Data Index: 3521404 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.0328. Min Act: -0.1700
Data Index: 1271138 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8453. Min Range: -6.8453
Max Act: 6.0328. Min Act: -0.1700
Data Index: 3255670 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8453. Min Range: -6.8453
Max Act: 5.9703. Min Act: -0.1700
Data Index: 5796698 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19