Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.5581. Min Act: -0.1700
Data Index: 5791415 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.5581. Min Act: -0.1700
Data Index: 6559247 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.4956. Min Act: -0.1700
Data Index: 2533273 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.4644. Min Act: -0.1700
Data Index: 856680 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.4331. Min Act: -0.1700
Data Index: 3773149 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.4019. Min Act: -0.1700
Data Index: 6630459 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.4019. Min Act: -0.1700
Data Index: 2484578 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3706. Min Act: -0.1700
Data Index: 6578969 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3706. Min Act: -0.1700
Data Index: 4425025 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3706. Min Act: -0.1700
Data Index: 6419965 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3394. Min Act: -0.1700
Data Index: 5784869 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3394. Min Act: -0.1700
Data Index: 7479851 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3081. Min Act: -0.1700
Data Index: 4509881 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3081. Min Act: -0.1700
Data Index: 8020353 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.3081. Min Act: -0.1700
Data Index: 5850913 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.2769. Min Act: -0.1700
Data Index: 956203 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.2769. Min Act: -0.1700
Data Index: 6278643 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.2769. Min Act: -0.1700
Data Index: 368781 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.2456. Min Act: -0.1700
Data Index: 5605406 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5581. Min Range: -4.5581
Max Act: 4.2769. Min Act: -0.1700
Data Index: 2897525 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19