Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4183 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1248. Min Range: -6.1248
Max Act: 6.1248. Min Act: -0.1700
Data Index: 751342 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1248. Min Range: -6.1248
Max Act: 6.0936. Min Act: -0.1700
Data Index: 7849570 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1248. Min Range: -6.1248
Max Act: 6.0623. Min Act: -0.1700
Data Index: 6607216 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1248. Min Range: -6.1248
Max Act: 6.0311. Min Act: -0.1700
Data Index: 8557304 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9998. Min Act: -0.1700
Data Index: 2321632 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9998. Min Act: -0.1700
Data Index: 3716751 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9686. Min Act: -0.1700
Data Index: 5003562 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9686. Min Act: -0.1700
Data Index: 5055338 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9061. Min Act: -0.1700
Data Index: 6955644 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9373. Min Act: -0.1700
Data Index: 537519 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9373. Min Act: -0.1700
Data Index: 5098368 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9373. Min Act: -0.1700
Data Index: 490991 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9373. Min Act: -0.1700
Data Index: 6445656 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9061. Min Act: -0.1700
Data Index: 780181 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9061. Min Act: -0.1700
Data Index: 3207442 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9061. Min Act: -0.1700
Data Index: 3679507 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9061. Min Act: -0.1700
Data Index: 1597610 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.8748. Min Act: -0.1700
Data Index: 5028654 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.9061. Min Act: -0.1700
Data Index: 663955 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1248. Min Range: -6.1248
Max Act: 5.8748. Min Act: -0.1700
Data Index: 6798499 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19