Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5370 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1373. Min Range: -6.1373
Max Act: 6.1373. Min Act: -0.1700
Data Index: 3715048 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1373. Min Range: -6.1373
Max Act: 6.0435. Min Act: -0.1700
Data Index: 1540919 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.9810. Min Act: -0.1700
Data Index: 3246128 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.9810. Min Act: -0.1700
Data Index: 368186 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.8873. Min Act: -0.1700
Data Index: 5005054 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7935. Min Act: -0.1700
Data Index: 8732473 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7623. Min Act: -0.1700
Data Index: 751245 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7310. Min Act: -0.1700
Data Index: 7522091 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.7310. Min Act: -0.1700
Data Index: 1194737 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.6060. Min Act: -0.1700
Data Index: 266963 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.5435. Min Act: -0.1700
Data Index: 8091183 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.5123. Min Act: -0.1700
Data Index: 6751111 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.5123. Min Act: -0.1700
Data Index: 2173839 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.4810. Min Act: -0.1700
Data Index: 5635548 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.4498. Min Act: -0.1700
Data Index: 4696000 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.4185. Min Act: -0.1700
Data Index: 546167 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.3873. Min Act: -0.1700
Data Index: 6084874 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.3873. Min Act: -0.1700
Data Index: 1026444 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.3560. Min Act: -0.1700
Data Index: 6796850 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1373. Min Range: -6.1373
Max Act: 5.3560. Min Act: -0.1700
Data Index: 5054904 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19