Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.8772. Min Act: -0.1700
Data Index: 8570063 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.8147. Min Act: -0.1700
Data Index: 5080602 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.2522. Min Act: -0.1700
Data Index: 7377279 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.1897. Min Act: -0.1700
Data Index: 2189157 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.1897. Min Act: -0.1700
Data Index: 7426935 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.1272. Min Act: -0.1700
Data Index: 5292000 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.0647. Min Act: -0.1700
Data Index: 8570338 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.0647. Min Act: -0.1700
Data Index: 6100771 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8772. Min Range: -8.8772
Max Act: 8.0022. Min Act: -0.1700
Data Index: 5519781 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.9397. Min Act: -0.1700
Data Index: 6398856 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.9397. Min Act: -0.1700
Data Index: 6885466 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.9397. Min Act: -0.1700
Data Index: 2065813 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.9397. Min Act: -0.1700
Data Index: 172693 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.8772. Min Act: -0.1700
Data Index: 792051 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.8772. Min Act: -0.1700
Data Index: 2411017 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.8772. Min Act: -0.1700
Data Index: 4702148 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.9397. Min Act: -0.1700
Data Index: 5341621 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.8147. Min Act: -0.1700
Data Index: 6036840 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.8147. Min Act: -0.1700
Data Index: 352379 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8772. Min Range: -8.8772
Max Act: 7.8147. Min Act: -0.1700
Data Index: 6928327 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19