Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.5533. Min Act: -0.1700
Data Index: 577978 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.5220. Min Act: -0.1700
Data Index: 3053277 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.5220. Min Act: -0.1700
Data Index: 1393145 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.4908. Min Act: -0.1700
Data Index: 8685172 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.4595. Min Act: -0.1700
Data Index: 4851181 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.4595. Min Act: -0.1700
Data Index: 4887518 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.4283. Min Act: -0.1700
Data Index: 5992392 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3658. Min Act: -0.1700
Data Index: 1643579 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3658. Min Act: -0.1700
Data Index: 5415252 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3658. Min Act: -0.1700
Data Index: 139236 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3345. Min Act: -0.1700
Data Index: 3120380 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3345. Min Act: -0.1700
Data Index: 4610519 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3345. Min Act: -0.1700
Data Index: 5474111 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3345. Min Act: -0.1700
Data Index: 3662946 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3033. Min Act: -0.1700
Data Index: 8001671 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3033. Min Act: -0.1700
Data Index: 6853909 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3033. Min Act: -0.1700
Data Index: 245333 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3033. Min Act: -0.1700
Data Index: 3955628 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3033. Min Act: -0.1700
Data Index: 2402544 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5533. Min Range: -4.5533
Max Act: 4.3033. Min Act: -0.1700
Data Index: 7715021 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19