Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.2992. Min Act: -0.1700
Data Index: 4064258 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.1742. Min Act: -0.1700
Data Index: 1017191 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.1429. Min Act: -0.1700
Data Index: 6589877 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.1117. Min Act: -0.1700
Data Index: 4808971 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.0804. Min Act: -0.1700
Data Index: 6222284 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.0804. Min Act: -0.1700
Data Index: 3749207 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.0492. Min Act: -0.1700
Data Index: 343206 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.0179. Min Act: -0.1700
Data Index: 6944387 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2992. Min Range: -5.2992
Max Act: 5.0179. Min Act: -0.1700
Data Index: 5024730 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.9867. Min Act: -0.1700
Data Index: 2766701 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.9554. Min Act: -0.1700
Data Index: 2184113 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.9242. Min Act: -0.1700
Data Index: 6746745 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3539237 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.8617. Min Act: -0.1700
Data Index: 2184115 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.8617. Min Act: -0.1700
Data Index: 2184111 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.7992. Min Act: -0.1700
Data Index: 2133444 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.7992. Min Act: -0.1700
Data Index: 4643441 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.7679. Min Act: -0.1700
Data Index: 4929320 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.7992. Min Act: -0.1700
Data Index: 398669 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2992. Min Range: -5.2992
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3750070 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19