Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5374 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.8485. Min Act: -0.1700
Data Index: 6883643 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.5985. Min Act: -0.1700
Data Index: 6860984 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.4735. Min Act: -0.1700
Data Index: 596516 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.2235. Min Act: -0.1700
Data Index: 5480425 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.1610. Min Act: -0.1700
Data Index: 5480428 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.0985. Min Act: -0.1700
Data Index: 8672880 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8485. Min Range: -8.8485
Max Act: 8.0360. Min Act: -0.1700
Data Index: 4143171 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.9735. Min Act: -0.1700
Data Index: 7940461 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.9110. Min Act: -0.1700
Data Index: 4728460 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.7860. Min Act: -0.1700
Data Index: 4510873 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.8485. Min Act: -0.1700
Data Index: 1936866 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.8485. Min Act: -0.1700
Data Index: 2638318 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.8485. Min Act: -0.1700
Data Index: 7387681 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.8485. Min Act: -0.1700
Data Index: 7206702 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.7860. Min Act: -0.1700
Data Index: 6783843 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.8485. Min Act: -0.1700
Data Index: 6987773 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.8485. Min Act: -0.1700
Data Index: 8088815 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.7860. Min Act: -0.1700
Data Index: 3261011 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.7860. Min Act: -0.1700
Data Index: 949723 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8485. Min Range: -8.8485
Max Act: 7.7860. Min Act: -0.1700
Data Index: 2154794 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19