Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1069. Min Range: -8.1069
Max Act: 8.1069. Min Act: -0.1700
Data Index: 1778246 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1069. Min Range: -8.1069
Max Act: 8.0444. Min Act: -0.1700
Data Index: 5137961 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.8569. Min Act: -0.1700
Data Index: 2470664 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.7944. Min Act: -0.1700
Data Index: 273057 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.7944. Min Act: -0.1700
Data Index: 2318573 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.6694. Min Act: -0.1700
Data Index: 8582127 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.6694. Min Act: -0.1700
Data Index: 1149722 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.6381. Min Act: -0.1700
Data Index: 8310628 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.6069. Min Act: -0.1700
Data Index: 3733792 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.5444. Min Act: -0.1700
Data Index: 5157565 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.5444. Min Act: -0.1700
Data Index: 4748102 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4819. Min Act: -0.1700
Data Index: 3806831 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4819. Min Act: -0.1700
Data Index: 2402487 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4819. Min Act: -0.1700
Data Index: 8727000 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4506. Min Act: -0.1700
Data Index: 4192139 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4506. Min Act: -0.1700
Data Index: 1641792 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4194. Min Act: -0.1700
Data Index: 8343994 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.4194. Min Act: -0.1700
Data Index: 3156714 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.3881. Min Act: -0.1700
Data Index: 1514270 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1069. Min Range: -8.1069
Max Act: 7.3569. Min Act: -0.1700
Data Index: 3504610 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19