Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.4659. Min Act: -0.1700
Data Index: 3629365 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.4347. Min Act: -0.1700
Data Index: 3776109 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.4347. Min Act: -0.1700
Data Index: 1703723 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.3722. Min Act: -0.1700
Data Index: 6161907 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.2784. Min Act: -0.1700
Data Index: 2977970 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.2472. Min Act: -0.1700
Data Index: 8264849 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.2472. Min Act: -0.1700
Data Index: 8061825 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.2472. Min Act: -0.1700
Data Index: 5673565 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.2159. Min Act: -0.1700
Data Index: 2501411 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.2159. Min Act: -0.1700
Data Index: 997259 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1847. Min Act: -0.1700
Data Index: 1294814 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1847. Min Act: -0.1700
Data Index: 7979148 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1534. Min Act: -0.1700
Data Index: 2647099 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1534. Min Act: -0.1700
Data Index: 6220654 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1534. Min Act: -0.1700
Data Index: 204896 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1534. Min Act: -0.1700
Data Index: 5726021 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1534. Min Act: -0.1700
Data Index: 1210285 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.1534. Min Act: -0.1700
Data Index: 6859915 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.0909. Min Act: -0.1700
Data Index: 6830692 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4659. Min Range: -5.4659
Max Act: 5.0909. Min Act: -0.1700
Data Index: 4309786 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19