Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1420 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.6083. Min Act: -0.1700
Data Index: 6190307 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.5771. Min Act: -0.1700
Data Index: 4501103 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.5458. Min Act: -0.1700
Data Index: 1174244 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.2958. Min Act: -0.1700
Data Index: 8562683 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.2646. Min Act: -0.1700
Data Index: 585201 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.2646. Min Act: -0.1700
Data Index: 3396862 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.2021. Min Act: -0.1700
Data Index: 2024241 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.2021. Min Act: -0.1700
Data Index: 5334514 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.2333. Min Act: -0.1700
Data Index: 2176994 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1708. Min Act: -0.1700
Data Index: 5884195 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1708. Min Act: -0.1700
Data Index: 851423 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1396. Min Act: -0.1700
Data Index: 3198337 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1396. Min Act: -0.1700
Data Index: 5648656 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1396. Min Act: -0.1700
Data Index: 1025749 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1083. Min Act: -0.1700
Data Index: 8636502 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1083. Min Act: -0.1700
Data Index: 188468 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1083. Min Act: -0.1700
Data Index: 6590687 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1083. Min Act: -0.1700
Data Index: 8455138 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.1396. Min Act: -0.1700
Data Index: 4044105 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6083. Min Range: -5.6083
Max Act: 5.0458. Min Act: -0.1700
Data Index: 7104625 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19