Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.3568. Min Act: -0.1700
Data Index: 2083534 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.3568. Min Act: -0.1700
Data Index: 6554833 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.2005. Min Act: -0.1700
Data Index: 5954416 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.1380. Min Act: -0.1700
Data Index: 1126047 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.1067. Min Act: -0.1700
Data Index: 6687962 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.1067. Min Act: -0.1700
Data Index: 1331204 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.1067. Min Act: -0.1700
Data Index: 8436123 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0755. Min Act: -0.1700
Data Index: 1321617 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0755. Min Act: -0.1700
Data Index: 6652242 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0755. Min Act: -0.1700
Data Index: 3899763 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0755. Min Act: -0.1700
Data Index: 519733 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0755. Min Act: -0.1700
Data Index: 8445487 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0130. Min Act: -0.1700
Data Index: 549227 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0130. Min Act: -0.1700
Data Index: 8580259 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3568. Min Range: -4.3568
Max Act: 4.0130. Min Act: -0.1700
Data Index: 1809476 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3568. Min Range: -4.3568
Max Act: 3.9817. Min Act: -0.1700
Data Index: 6272526 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3568. Min Range: -4.3568
Max Act: 3.9817. Min Act: -0.1700
Data Index: 1745000 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3568. Min Range: -4.3568
Max Act: 3.9817. Min Act: -0.1700
Data Index: 6419586 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3568. Min Range: -4.3568
Max Act: 3.9817. Min Act: -0.1700
Data Index: 4487072 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3568. Min Range: -4.3568
Max Act: 3.9817. Min Act: -0.1700
Data Index: 730076 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19