Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.5928. Min Act: -0.1700
Data Index: 1480890 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.5928. Min Act: -0.1700
Data Index: 4097391 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.3741. Min Act: -0.1700
Data Index: 2046834 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.3428. Min Act: -0.1700
Data Index: 1924117 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.3428. Min Act: -0.1700
Data Index: 1298303 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.3116. Min Act: -0.1700
Data Index: 7636161 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.2491. Min Act: -0.1700
Data Index: 3722387 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.1866. Min Act: -0.1700
Data Index: 7672253 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.2178. Min Act: -0.1700
Data Index: 4780577 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.1553. Min Act: -0.1700
Data Index: 501794 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.1241. Min Act: -0.1700
Data Index: 889364 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0928. Min Act: -0.1700
Data Index: 5722050 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0928. Min Act: -0.1700
Data Index: 352845 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 7751900 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 3603657 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 7239527 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 7112657 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 2500623 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 6738458 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5928. Min Range: -7.5928
Max Act: 7.0616. Min Act: -0.1700
Data Index: 8771191 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19