Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.9201. Min Act: -0.1700
Data Index: 4802799 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.6076. Min Act: -0.1700
Data Index: 4388012 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.4826. Min Act: -0.1700
Data Index: 56780 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.4201. Min Act: -0.1700
Data Index: 5270966 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.3576. Min Act: -0.1700
Data Index: 8547024 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.3264. Min Act: -0.1700
Data Index: 1987521 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.2639. Min Act: -0.1700
Data Index: 8710116 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.2326. Min Act: -0.1700
Data Index: 8763525 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.1701. Min Act: -0.1700
Data Index: 7802506 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.1389. Min Act: -0.1700
Data Index: 2343317 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.1389. Min Act: -0.1700
Data Index: 7242223 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.1076. Min Act: -0.1700
Data Index: 3428102 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.1076. Min Act: -0.1700
Data Index: 1397913 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.0764. Min Act: -0.1700
Data Index: 8779676 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.1076. Min Act: -0.1700
Data Index: 8473839 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.0764. Min Act: -0.1700
Data Index: 6395098 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.0764. Min Act: -0.1700
Data Index: 8763341 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.0764. Min Act: -0.1700
Data Index: 6351471 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9201. Min Range: -7.9201
Max Act: 7.0451. Min Act: -0.1700
Data Index: 4356532 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9201. Min Range: -7.9201
Max Act: 6.9826. Min Act: -0.1700
Data Index: 4700048 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19