Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.4993. Min Act: -0.1700
Data Index: 3966680 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.4368. Min Act: -0.1700
Data Index: 473767 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.4056. Min Act: -0.1700
Data Index: 5135358 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.4056. Min Act: -0.1700
Data Index: 2887481 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.4368. Min Act: -0.1700
Data Index: 2131229 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.3431. Min Act: -0.1700
Data Index: 5435777 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.2806. Min Act: -0.1700
Data Index: 286588 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.2181. Min Act: -0.1700
Data Index: 4195944 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1868. Min Act: -0.1700
Data Index: 7754233 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1556. Min Act: -0.1700
Data Index: 1499734 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1556. Min Act: -0.1700
Data Index: 5675581 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.0931. Min Act: -0.1700
Data Index: 7354822 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1243. Min Act: -0.1700
Data Index: 2816134 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1243. Min Act: -0.1700
Data Index: 852448 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1243. Min Act: -0.1700
Data Index: 2178096 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3259300 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.0931. Min Act: -0.1700
Data Index: 6539572 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3878132 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.0931. Min Act: -0.1700
Data Index: 3923414 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4993. Min Range: -4.4993
Max Act: 4.1243. Min Act: -0.1700
Data Index: 6785723 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19