Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5258 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.9481. Min Act: -0.1700
Data Index: 1556973 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.8625. Min Act: -0.1700
Data Index: 6692929 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.8034. Min Act: -0.1698
Data Index: 4186933 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7700. Min Act: -0.1675
Data Index: 4474646 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7700. Min Act: -0.1700
Data Index: 6395561 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7368. Min Act: -0.1697
Data Index: 6772453 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7286. Min Act: -0.1700
Data Index: 3902404 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7122. Min Act: -0.1700
Data Index: 805474 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7122. Min Act: -0.1700
Data Index: 6818150 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7040. Min Act: -0.1700
Data Index: 4993822 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6958. Min Act: -0.1700
Data Index: 8505990 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7040. Min Act: -0.1700
Data Index: 2593423 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6958. Min Act: -0.1698
Data Index: 1451801 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.7040. Min Act: -0.1699
Data Index: 7619729 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6958. Min Act: -0.1700
Data Index: 2068064 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6877. Min Act: -0.1700
Data Index: 4926290 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6796. Min Act: -0.1698
Data Index: 6565544 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6715. Min Act: -0.1700
Data Index: 3884537 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6877. Min Act: -0.1690
Data Index: 7115089 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9481. Min Range: -0.9481
Max Act: 0.6796. Min Act: -0.1700
Data Index: 1730213 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19