Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2993. Min Range: -8.2993
Max Act: 8.2993. Min Act: -0.1700
Data Index: 1862865 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2993. Min Range: -8.2993
Max Act: 8.1743. Min Act: -0.1700
Data Index: 8544672 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2993. Min Range: -8.2993
Max Act: 8.1118. Min Act: -0.1700
Data Index: 1897049 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2993. Min Range: -8.2993
Max Act: 8.0180. Min Act: -0.1700
Data Index: 4375719 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2993. Min Range: -8.2993
Max Act: 8.0493. Min Act: -0.1700
Data Index: 2535063 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.9555. Min Act: -0.1700
Data Index: 5725291 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.8930. Min Act: -0.1700
Data Index: 407371 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.8930. Min Act: -0.1700
Data Index: 8453768 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.8618. Min Act: -0.1700
Data Index: 7638664 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.8618. Min Act: -0.1700
Data Index: 5100437 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.7993. Min Act: -0.1700
Data Index: 4931569 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.7680. Min Act: -0.1700
Data Index: 5730697 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.7368. Min Act: -0.1700
Data Index: 74187 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.7055. Min Act: -0.1700
Data Index: 4315624 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.6743. Min Act: -0.1700
Data Index: 7592602 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.6743. Min Act: -0.1700
Data Index: 7860515 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.6743. Min Act: -0.1700
Data Index: 1871963 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.6430. Min Act: -0.1700
Data Index: 4000228 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.6430. Min Act: -0.1700
Data Index: 1990254 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2993. Min Range: -8.2993
Max Act: 7.5805. Min Act: -0.1700
Data Index: 571680 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19