Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4121 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.5689. Min Act: -0.1700
Data Index: 185167 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.5689. Min Act: -0.1700
Data Index: 2497197 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.5376. Min Act: -0.1700
Data Index: 2279183 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.4439. Min Act: -0.1700
Data Index: 8253853 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.4439. Min Act: -0.1700
Data Index: 2825389 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.4126. Min Act: -0.1700
Data Index: 2009610 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.4439. Min Act: -0.1700
Data Index: 4209988 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.3814. Min Act: -0.1700
Data Index: 6564255 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.3814. Min Act: -0.1700
Data Index: 4594232 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.3501. Min Act: -0.1700
Data Index: 644549 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.3189. Min Act: -0.1700
Data Index: 2765744 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.3189. Min Act: -0.1700
Data Index: 1186340 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.2876. Min Act: -0.1700
Data Index: 2083835 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.2876. Min Act: -0.1700
Data Index: 7734802 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.2564. Min Act: -0.1700
Data Index: 6272785 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.2251. Min Act: -0.1700
Data Index: 7267666 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.1626. Min Act: -0.1700
Data Index: 181809 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.1626. Min Act: -0.1700
Data Index: 2636359 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.1626. Min Act: -0.1700
Data Index: 5420077 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5689. Min Range: -6.5689
Max Act: 6.1314. Min Act: -0.1700
Data Index: 1491000 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19