Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.8050. Min Act: -0.1700
Data Index: 2742657 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.7425. Min Act: -0.1700
Data Index: 8677602 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.7112. Min Act: -0.1700
Data Index: 6989416 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.5862. Min Act: -0.1700
Data Index: 7962209 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.5550. Min Act: -0.1700
Data Index: 6849813 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4925. Min Act: -0.1700
Data Index: 125839 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.5237. Min Act: -0.1700
Data Index: 7647437 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4925. Min Act: -0.1700
Data Index: 800932 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4925. Min Act: -0.1700
Data Index: 325478 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4300. Min Act: -0.1700
Data Index: 4507833 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4300. Min Act: -0.1700
Data Index: 3939832 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4300. Min Act: -0.1700
Data Index: 6542903 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4300. Min Act: -0.1700
Data Index: 2299995 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4612. Min Act: -0.1700
Data Index: 9207 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.4300. Min Act: -0.1700
Data Index: 449949 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.3987. Min Act: -0.1700
Data Index: 2399467 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.3987. Min Act: -0.1700
Data Index: 3969607 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.3987. Min Act: -0.1700
Data Index: 5087541 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.3987. Min Act: -0.1700
Data Index: 6658509 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8050. Min Range: -6.8050
Max Act: 6.3987. Min Act: -0.1700
Data Index: 5852644 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19