Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.9313. Min Act: -0.1700
Data Index: 682680 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.8688. Min Act: -0.1700
Data Index: 2109689 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.6188. Min Act: -0.1700
Data Index: 5682315 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.6188. Min Act: -0.1700
Data Index: 3855185 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5876. Min Act: -0.1700
Data Index: 7468733 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5251. Min Act: -0.1700
Data Index: 2913996 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.5251. Min Act: -0.1700
Data Index: 5172769 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4938. Min Act: -0.1700
Data Index: 2523613 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4626. Min Act: -0.1700
Data Index: 6414575 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4626. Min Act: -0.1700
Data Index: 5330212 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4626. Min Act: -0.1700
Data Index: 5945028 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4626. Min Act: -0.1700
Data Index: 3376734 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4313. Min Act: -0.1700
Data Index: 6918673 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4313. Min Act: -0.1700
Data Index: 1649861 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4313. Min Act: -0.1700
Data Index: 1445360 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4001. Min Act: -0.1700
Data Index: 888004 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4001. Min Act: -0.1700
Data Index: 1179870 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4313. Min Act: -0.1700
Data Index: 3157450 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.4001. Min Act: -0.1700
Data Index: 6383533 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9313. Min Range: -6.9313
Max Act: 6.3688. Min Act: -0.1700
Data Index: 4872188 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19