Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.3730. Min Act: -0.1700
Data Index: 2640632 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.4042. Min Act: -0.1700
Data Index: 4270550 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.3417. Min Act: -0.1700
Data Index: 5125701 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.3105. Min Act: -0.1700
Data Index: 7737322 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.3417. Min Act: -0.1700
Data Index: 1375675 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.2792. Min Act: -0.1700
Data Index: 373026 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.2480. Min Act: -0.1700
Data Index: 8624218 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.2480. Min Act: -0.1700
Data Index: 6127510 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.2480. Min Act: -0.1700
Data Index: 7011116 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.2167. Min Act: -0.1700
Data Index: 1260325 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.2167. Min Act: -0.1700
Data Index: 6836824 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1855. Min Act: -0.1700
Data Index: 5108540 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1855. Min Act: -0.1700
Data Index: 5254719 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1542. Min Act: -0.1700
Data Index: 3954125 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1855. Min Act: -0.1700
Data Index: 6962044 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1855. Min Act: -0.1700
Data Index: 2027558 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1855. Min Act: -0.1700
Data Index: 5167316 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1855. Min Act: -0.1700
Data Index: 390715 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1542. Min Act: -0.1700
Data Index: 3954123 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4042. Min Range: -5.4042
Max Act: 5.1542. Min Act: -0.1700
Data Index: 2027556 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19