Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5705 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0670. Min Range: -5.0670
Max Act: 5.0670. Min Act: -0.1700
Data Index: 3104804 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0670. Min Range: -5.0670
Max Act: 5.0357. Min Act: -0.1700
Data Index: 5151636 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0670. Min Range: -5.0670
Max Act: 5.0357. Min Act: -0.1700
Data Index: 4099463 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9732. Min Act: -0.1700
Data Index: 4288777 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9420. Min Act: -0.1700
Data Index: 5926521 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9420. Min Act: -0.1700
Data Index: 6645088 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9420. Min Act: -0.1700
Data Index: 1541516 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9420. Min Act: -0.1700
Data Index: 8035785 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9107. Min Act: -0.1700
Data Index: 7126524 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.9107. Min Act: -0.1700
Data Index: 4430937 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 5813462 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 8011223 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 722248 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 2214776 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 1541515 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 3139685 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8795. Min Act: -0.1700
Data Index: 5693560 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8482. Min Act: -0.1700
Data Index: 2287321 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8482. Min Act: -0.1700
Data Index: 4850463 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0670. Min Range: -5.0670
Max Act: 4.8170. Min Act: -0.1700
Data Index: 662228 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19