Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.6588. Min Act: -0.1700
Data Index: 4330809 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4713. Min Act: -0.1700
Data Index: 3715084 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4713. Min Act: -0.1700
Data Index: 4390292 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4713. Min Act: -0.1700
Data Index: 5803975 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4713. Min Act: -0.1700
Data Index: 1701945 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4400. Min Act: -0.1700
Data Index: 572938 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4400. Min Act: -0.1700
Data Index: 8230636 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4088. Min Act: -0.1700
Data Index: 8511625 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4088. Min Act: -0.1700
Data Index: 4748178 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4088. Min Act: -0.1700
Data Index: 6660565 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3775. Min Act: -0.1700
Data Index: 4330799 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.4088. Min Act: -0.1700
Data Index: 5792627 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3463. Min Act: -0.1700
Data Index: 7397705 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3463. Min Act: -0.1700
Data Index: 3914494 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3463. Min Act: -0.1700
Data Index: 368161 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3463. Min Act: -0.1700
Data Index: 7822327 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3150. Min Act: -0.1700
Data Index: 572941 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3150. Min Act: -0.1700
Data Index: 3854570 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.2838. Min Act: -0.1700
Data Index: 4760511 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6588. Min Range: -5.6588
Max Act: 5.3150. Min Act: -0.1700
Data Index: 5801303 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19