Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1471 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.5465. Min Act: -0.1700
Data Index: 5834641 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.5152. Min Act: -0.1700
Data Index: 5583795 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.4526. Min Act: -0.1700
Data Index: 2428643 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.4526. Min Act: -0.1700
Data Index: 7463834 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.4055. Min Act: -0.1700
Data Index: 2096128 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.4055. Min Act: -0.1700
Data Index: 6565499 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.3428. Min Act: -0.1700
Data Index: 7403555 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.3428. Min Act: -0.1700
Data Index: 3139026 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.3114. Min Act: -0.1700
Data Index: 3034616 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2800. Min Act: -0.1700
Data Index: 7974666 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2800. Min Act: -0.1700
Data Index: 2778792 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2800. Min Act: -0.1700
Data Index: 6967637 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2329. Min Act: -0.1700
Data Index: 889577 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2486. Min Act: -0.1700
Data Index: 6377221 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2329. Min Act: -0.1700
Data Index: 6836605 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2172. Min Act: -0.1700
Data Index: 7416765 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2172. Min Act: -0.1700
Data Index: 7003134 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2015. Min Act: -0.1700
Data Index: 655064 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.1857. Min Act: -0.1700
Data Index: 7294599 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5465. Min Range: -3.5465
Max Act: 3.2015. Min Act: -0.1700
Data Index: 3553767 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19