Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.8374. Min Act: -0.1700
Data Index: 3675319 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.7124. Min Act: -0.1700
Data Index: 6166127 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.6811. Min Act: -0.1700
Data Index: 6758548 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.6186. Min Act: -0.1700
Data Index: 2707080 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.6186. Min Act: -0.1700
Data Index: 7147965 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.5561. Min Act: -0.1700
Data Index: 4426799 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.5249. Min Act: -0.1700
Data Index: 272571 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4936. Min Act: -0.1700
Data Index: 5795578 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4936. Min Act: -0.1700
Data Index: 7539073 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4624. Min Act: -0.1700
Data Index: 8129536 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4624. Min Act: -0.1700
Data Index: 3234939 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.4311. Min Act: -0.1700
Data Index: 6102247 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3999. Min Act: -0.1700
Data Index: 281229 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3686. Min Act: -0.1700
Data Index: 5558308 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3999. Min Act: -0.1700
Data Index: 549097 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3999. Min Act: -0.1700
Data Index: 3818573 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3374. Min Act: -0.1700
Data Index: 5919200 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3374. Min Act: -0.1700
Data Index: 6653622 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3061. Min Act: -0.1700
Data Index: 8441864 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8374. Min Range: -6.8374
Max Act: 6.3374. Min Act: -0.1700
Data Index: 881151 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19