Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.6729. Min Act: -0.1700
Data Index: 1790916 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.3604. Min Act: -0.1700
Data Index: 4223961 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.2666. Min Act: -0.1700
Data Index: 3265642 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.2666. Min Act: -0.1700
Data Index: 6541460 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.2666. Min Act: -0.1700
Data Index: 6309312 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.2041. Min Act: -0.1700
Data Index: 1811104 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.1416. Min Act: -0.1700
Data Index: 2040949 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0791. Min Act: -0.1700
Data Index: 550253 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0791. Min Act: -0.1700
Data Index: 1860589 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0791. Min Act: -0.1700
Data Index: 1262411 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0479. Min Act: -0.1700
Data Index: 5508319 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0479. Min Act: -0.1700
Data Index: 7581429 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0166. Min Act: -0.1700
Data Index: 3521407 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6729. Min Range: -6.6729
Max Act: 6.0166. Min Act: -0.1700
Data Index: 7234201 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6729. Min Range: -6.6729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 594567 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6729. Min Range: -6.6729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 8261654 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6729. Min Range: -6.6729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2948728 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6729. Min Range: -6.6729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 311104 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6729. Min Range: -6.6729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2702817 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6729. Min Range: -6.6729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 100606 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19