Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5189 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.1783. Min Act: -0.1700
Data Index: 6296625 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.1471. Min Act: -0.1700
Data Index: 455291 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.1783. Min Act: -0.1700
Data Index: 6806221 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.1158. Min Act: -0.1700
Data Index: 6396473 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.1158. Min Act: -0.1700
Data Index: 4542337 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.0846. Min Act: -0.1700
Data Index: 6157762 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.0846. Min Act: -0.1700
Data Index: 3375161 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.0533. Min Act: -0.1700
Data Index: 4020619 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.0533. Min Act: -0.1700
Data Index: 7564054 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1783. Min Range: -7.1783
Max Act: 7.0221. Min Act: -0.1700
Data Index: 3625514 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.9908. Min Act: -0.1700
Data Index: 3893596 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.9596. Min Act: -0.1700
Data Index: 1712796 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.9283. Min Act: -0.1700
Data Index: 5285969 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.9283. Min Act: -0.1700
Data Index: 114158 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.9283. Min Act: -0.1700
Data Index: 2539255 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.8971. Min Act: -0.1700
Data Index: 210773 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.8971. Min Act: -0.1700
Data Index: 2135869 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.8971. Min Act: -0.1700
Data Index: 3039190 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.8971. Min Act: -0.1700
Data Index: 1652656 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1783. Min Range: -7.1783
Max Act: 6.8658. Min Act: -0.1700
Data Index: 3293827 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19