Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.8033. Min Act: -0.1700
Data Index: 7015171 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.7408. Min Act: -0.1700
Data Index: 5135023 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.7095. Min Act: -0.1700
Data Index: 4808204 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.6783. Min Act: -0.1700
Data Index: 301081 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.6783. Min Act: -0.1700
Data Index: 7482545 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.6158. Min Act: -0.1700
Data Index: 566322 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.6470. Min Act: -0.1700
Data Index: 5349141 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5845. Min Act: -0.1700
Data Index: 2680222 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5845. Min Act: -0.1700
Data Index: 3450892 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5845. Min Act: -0.1700
Data Index: 7478794 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5533. Min Act: -0.1700
Data Index: 6164390 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5845. Min Act: -0.1700
Data Index: 7925959 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4908. Min Act: -0.1700
Data Index: 4106660 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.5220. Min Act: -0.1700
Data Index: 4985846 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4595. Min Act: -0.1700
Data Index: 1402479 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 3491185 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4595. Min Act: -0.1700
Data Index: 3103683 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3970. Min Act: -0.1700
Data Index: 434485 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.4283. Min Act: -0.1700
Data Index: 8100692 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8033. Min Range: -6.8033
Max Act: 6.3970. Min Act: -0.1700
Data Index: 6480303 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19