Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.7280. Min Act: -0.1700
Data Index: 1397188 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.5093. Min Act: -0.1700
Data Index: 1053412 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.4468. Min Act: -0.1700
Data Index: 435650 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.3530. Min Act: -0.1700
Data Index: 926009 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.3530. Min Act: -0.1700
Data Index: 884913 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.3218. Min Act: -0.1700
Data Index: 2277469 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1968. Min Act: -0.1700
Data Index: 7572683 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1968. Min Act: -0.1700
Data Index: 474009 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1968. Min Act: -0.1700
Data Index: 291540 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1968. Min Act: -0.1700
Data Index: 3656421 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1655. Min Act: -0.1700
Data Index: 7046931 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1343. Min Act: -0.1700
Data Index: 7475851 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.1030. Min Act: -0.1700
Data Index: 4093725 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0718. Min Act: -0.1700
Data Index: 6099833 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0718. Min Act: -0.1700
Data Index: 1204848 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0405. Min Act: -0.1700
Data Index: 4674963 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0405. Min Act: -0.1700
Data Index: 4880465 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0093. Min Act: -0.1700
Data Index: 3597924 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0093. Min Act: -0.1700
Data Index: 8202634 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7280. Min Range: -6.7280
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4449531 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19