Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.7814. Min Act: -0.1700
Data Index: 8716487 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.7189. Min Act: -0.1700
Data Index: 2297404 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.6876. Min Act: -0.1700
Data Index: 1805976 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.7189. Min Act: -0.1700
Data Index: 7384241 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.6564. Min Act: -0.1700
Data Index: 8083287 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.6564. Min Act: -0.1700
Data Index: 2736151 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5939. Min Act: -0.1700
Data Index: 1267402 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.6251. Min Act: -0.1700
Data Index: 4742379 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5939. Min Act: -0.1700
Data Index: 7861648 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5939. Min Act: -0.1700
Data Index: 8673147 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5939. Min Act: -0.1700
Data Index: 3464475 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5626. Min Act: -0.1700
Data Index: 7861646 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5626. Min Act: -0.1700
Data Index: 6965840 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5314. Min Act: -0.1700
Data Index: 638004 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5314. Min Act: -0.1700
Data Index: 3341363 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5001. Min Act: -0.1700
Data Index: 1143824 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5314. Min Act: -0.1700
Data Index: 262878 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.5001. Min Act: -0.1700
Data Index: 6991925 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.4689. Min Act: -0.1700
Data Index: 7784602 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7814. Min Range: -6.7814
Max Act: 6.4689. Min Act: -0.1700
Data Index: 322542 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19