Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6055. Min Range: -7.6055
Max Act: 7.6055. Min Act: -0.1700
Data Index: 7686987 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6055. Min Range: -7.6055
Max Act: 7.2930. Min Act: -0.1700
Data Index: 5082923 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6055. Min Range: -7.6055
Max Act: 7.3243. Min Act: -0.1700
Data Index: 1353304 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.9805. Min Act: -0.1700
Data Index: 6180239 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6055. Min Range: -7.6055
Max Act: 7.0118. Min Act: -0.1700
Data Index: 431922 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.9805. Min Act: -0.1700
Data Index: 3015538 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.9493. Min Act: -0.1700
Data Index: 7891028 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8868. Min Act: -0.1700
Data Index: 3529419 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.9805. Min Act: -0.1700
Data Index: 8132261 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8868. Min Act: -0.1700
Data Index: 1639952 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8868. Min Act: -0.1700
Data Index: 6166754 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8868. Min Act: -0.1700
Data Index: 21586 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8868. Min Act: -0.1700
Data Index: 645301 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8555. Min Act: -0.1700
Data Index: 3945081 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8555. Min Act: -0.1700
Data Index: 6138380 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8555. Min Act: -0.1700
Data Index: 5636554 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.7618. Min Act: -0.1700
Data Index: 8182842 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8243. Min Act: -0.1700
Data Index: 4119521 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8555. Min Act: -0.1700
Data Index: 7083290 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6055. Min Range: -7.6055
Max Act: 6.8555. Min Act: -0.1700
Data Index: 4862767 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19