Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.9861. Min Act: -0.1700
Data Index: 3348088 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.9236. Min Act: -0.1700
Data Index: 3554697 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7828. Min Act: -0.1700
Data Index: 2446555 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7985. Min Act: -0.1700
Data Index: 4338567 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7672. Min Act: -0.1700
Data Index: 4338570 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7359. Min Act: -0.1700
Data Index: 454940 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7359. Min Act: -0.1700
Data Index: 595853 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7203. Min Act: -0.1700
Data Index: 1957269 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7203. Min Act: -0.1700
Data Index: 5384402 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7203. Min Act: -0.1700
Data Index: 3554695 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7046. Min Act: -0.1700
Data Index: 3554696 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7046. Min Act: -0.1700
Data Index: 5059665 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.7046. Min Act: -0.1700
Data Index: 59638 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6890. Min Act: -0.1700
Data Index: 3554680 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6734. Min Act: -0.1700
Data Index: 2710359 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6734. Min Act: -0.1700
Data Index: 4384664 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6734. Min Act: -0.1700
Data Index: 1138181 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6421. Min Act: -0.1700
Data Index: 8645927 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6108. Min Act: -0.1700
Data Index: 3849399 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9861. Min Range: -3.9861
Max Act: 3.6108. Min Act: -0.1700
Data Index: 6368338 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19