Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.4754. Min Act: -0.1700
Data Index: 3614120 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.3500. Min Act: -0.1700
Data Index: 1194465 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.3500. Min Act: -0.1700
Data Index: 7621767 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.3343. Min Act: -0.1700
Data Index: 5165125 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.3343. Min Act: -0.1700
Data Index: 6836193 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.3029. Min Act: -0.1700
Data Index: 4872029 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2872. Min Act: -0.1700
Data Index: 2648994 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2872. Min Act: -0.1700
Data Index: 3508373 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2872. Min Act: -0.1700
Data Index: 6569415 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2872. Min Act: -0.1700
Data Index: 634040 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2715. Min Act: -0.1700
Data Index: 4313951 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2715. Min Act: -0.1700
Data Index: 3667339 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2715. Min Act: -0.1700
Data Index: 4186304 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2715. Min Act: -0.1700
Data Index: 1028078 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2401. Min Act: -0.1700
Data Index: 7444563 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2558. Min Act: -0.1700
Data Index: 8401552 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2558. Min Act: -0.1700
Data Index: 2544055 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2401. Min Act: -0.1700
Data Index: 5471474 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2244. Min Act: -0.1700
Data Index: 11929 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4754. Min Range: -3.4754
Max Act: 3.2558. Min Act: -0.1700
Data Index: 3570002 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19