Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.9663. Min Act: -0.1700
Data Index: 5918781 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.8726. Min Act: -0.1700
Data Index: 6170592 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.7788. Min Act: -0.1700
Data Index: 8217461 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.7476. Min Act: -0.1700
Data Index: 44008 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.7476. Min Act: -0.1700
Data Index: 1112877 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6851. Min Act: -0.1700
Data Index: 1662640 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6851. Min Act: -0.1700
Data Index: 1917093 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6538. Min Act: -0.1700
Data Index: 8288513 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6851. Min Act: -0.1700
Data Index: 195124 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6538. Min Act: -0.1700
Data Index: 6687939 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6538. Min Act: -0.1700
Data Index: 4681362 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6226. Min Act: -0.1700
Data Index: 4889596 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6538. Min Act: -0.1700
Data Index: 4156398 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6226. Min Act: -0.1700
Data Index: 5109445 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.6538. Min Act: -0.1700
Data Index: 1692873 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.5601. Min Act: -0.1700
Data Index: 1112881 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.5913. Min Act: -0.1700
Data Index: 4430584 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.5913. Min Act: -0.1700
Data Index: 2319502 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.5913. Min Act: -0.1700
Data Index: 8591616 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9663. Min Range: -6.9663
Max Act: 6.5601. Min Act: -0.1700
Data Index: 5893117 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19