Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.3187. Min Act: -0.1700
Data Index: 4711004 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.2562. Min Act: -0.1700
Data Index: 7812436 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.1937. Min Act: -0.1700
Data Index: 313836 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.1312. Min Act: -0.1700
Data Index: 8688530 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.1624. Min Act: -0.1700
Data Index: 2811807 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0999. Min Act: -0.1700
Data Index: 148509 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.1312. Min Act: -0.1700
Data Index: 2954525 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0999. Min Act: -0.1700
Data Index: 694082 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0687. Min Act: -0.1700
Data Index: 1614227 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0374. Min Act: -0.1700
Data Index: 1816511 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0062. Min Act: -0.1700
Data Index: 917638 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0374. Min Act: -0.1700
Data Index: 6136574 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3187. Min Range: -6.3187
Max Act: 6.0062. Min Act: -0.1700
Data Index: 1986386 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9749. Min Act: -0.1700
Data Index: 7927025 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9437. Min Act: -0.1700
Data Index: 816466 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9437. Min Act: -0.1700
Data Index: 773077 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9124. Min Act: -0.1700
Data Index: 207628 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9124. Min Act: -0.1700
Data Index: 747170 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7545990 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3187. Min Range: -6.3187
Max Act: 5.9124. Min Act: -0.1700
Data Index: 1130239 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19