Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3060. Min Range: -6.3060
Max Act: 6.3060. Min Act: -0.1700
Data Index: 441924 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3060. Min Range: -6.3060
Max Act: 6.1497. Min Act: -0.1700
Data Index: 4672720 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3060. Min Range: -6.3060
Max Act: 6.0872. Min Act: -0.1700
Data Index: 6692775 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3060. Min Range: -6.3060
Max Act: 6.0560. Min Act: -0.1700
Data Index: 1694433 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3060. Min Range: -6.3060
Max Act: 6.0247. Min Act: -0.1700
Data Index: 3496260 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.9935. Min Act: -0.1700
Data Index: 3249137 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.9935. Min Act: -0.1700
Data Index: 6789272 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.8997. Min Act: -0.1700
Data Index: 5851058 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.9310. Min Act: -0.1700
Data Index: 8519342 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.8372. Min Act: -0.1700
Data Index: 7566649 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.8372. Min Act: -0.1700
Data Index: 274529 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.8060. Min Act: -0.1700
Data Index: 8233941 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.8372. Min Act: -0.1700
Data Index: 632822 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.8060. Min Act: -0.1700
Data Index: 5757118 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.7747. Min Act: -0.1700
Data Index: 3435334 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.7747. Min Act: -0.1700
Data Index: 4778161 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.7747. Min Act: -0.1700
Data Index: 2106683 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.7747. Min Act: -0.1700
Data Index: 6880324 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.7435. Min Act: -0.1700
Data Index: 1419831 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3060. Min Range: -6.3060
Max Act: 5.7435. Min Act: -0.1700
Data Index: 8288692 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19