Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6377 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.8238. Min Act: -0.1699
Data Index: 6481489 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.8079. Min Act: -0.1700
Data Index: 5454241 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.8079. Min Act: -0.1700
Data Index: 8768422 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.7442. Min Act: -0.1700
Data Index: 1430154 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.7282. Min Act: -0.1700
Data Index: 6404505 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.7122. Min Act: -0.1700
Data Index: 3557694 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6802. Min Act: -0.1700
Data Index: 1682459 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6802. Min Act: -0.1700
Data Index: 6391792 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6481. Min Act: -0.1700
Data Index: 758529 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6321. Min Act: -0.1700
Data Index: 3497296 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6321. Min Act: -0.1700
Data Index: 1218899 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6321. Min Act: -0.1700
Data Index: 6754123 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6160. Min Act: -0.1700
Data Index: 8220562 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6321. Min Act: -0.1700
Data Index: 1405606 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.6160. Min Act: -0.1700
Data Index: 1871885 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.5838. Min Act: -0.1700
Data Index: 1995647 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.5999. Min Act: -0.1700
Data Index: 4037165 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.5999. Min Act: -0.1700
Data Index: 3103451 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.5999. Min Act: -0.1700
Data Index: 3699033 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8238. Min Range: -2.8238
Max Act: 2.5999. Min Act: -0.1700
Data Index: 3498419 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19