Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 977 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.8486. Min Act: -0.1700
Data Index: 1319613 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.7548. Min Act: -0.1700
Data Index: 5727191 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.7236. Min Act: -0.1700
Data Index: 189256 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.5048. Min Act: -0.1700
Data Index: 8824921 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.5048. Min Act: -0.1700
Data Index: 945966 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.4736. Min Act: -0.1700
Data Index: 3735585 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.4111. Min Act: -0.1700
Data Index: 4688917 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3798. Min Act: -0.1700
Data Index: 2242504 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3486. Min Act: -0.1700
Data Index: 602666 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3486. Min Act: -0.1700
Data Index: 4184739 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.2861. Min Act: -0.1700
Data Index: 5828073 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3173. Min Act: -0.1700
Data Index: 178871 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3173. Min Act: -0.1700
Data Index: 6580714 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3173. Min Act: -0.1700
Data Index: 1670301 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.3173. Min Act: -0.1700
Data Index: 908987 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.2861. Min Act: -0.1700
Data Index: 6771977 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.2861. Min Act: -0.1700
Data Index: 8763404 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.2548. Min Act: -0.1700
Data Index: 3721864 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.2548. Min Act: -0.1700
Data Index: 2868231 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8486. Min Range: -5.8486
Max Act: 5.2236. Min Act: -0.1700
Data Index: 5873094 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19