Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1345 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.8410. Min Act: -0.1700
Data Index: 2883889 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.7160. Min Act: -0.1700
Data Index: 569384 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.6535. Min Act: -0.1700
Data Index: 3865163 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.6223. Min Act: -0.1700
Data Index: 1932387 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.5285. Min Act: -0.1700
Data Index: 890720 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4973. Min Act: -0.1700
Data Index: 2584336 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4660. Min Act: -0.1700
Data Index: 3749718 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4660. Min Act: -0.1700
Data Index: 6707666 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4348. Min Act: -0.1700
Data Index: 7161627 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4348. Min Act: -0.1700
Data Index: 789617 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4035. Min Act: -0.1700
Data Index: 5122546 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.4035. Min Act: -0.1700
Data Index: 4459020 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.3410. Min Act: -0.1700
Data Index: 5191093 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.3410. Min Act: -0.1700
Data Index: 1478757 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.3410. Min Act: -0.1700
Data Index: 2340162 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.3410. Min Act: -0.1700
Data Index: 4181055 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.3098. Min Act: -0.1700
Data Index: 4600353 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.3098. Min Act: -0.1700
Data Index: 6978990 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.2785. Min Act: -0.1700
Data Index: 2767204 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8410. Min Range: -7.8410
Max Act: 7.2785. Min Act: -0.1700
Data Index: 3380804 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19