Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.7602. Min Act: -0.1700
Data Index: 15124 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.7289. Min Act: -0.1700
Data Index: 3977607 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.6977. Min Act: -0.1700
Data Index: 924054 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.6352. Min Act: -0.1700
Data Index: 3479189 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5727. Min Act: -0.1700
Data Index: 6001099 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.6039. Min Act: -0.1700
Data Index: 3436634 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5727. Min Act: -0.1700
Data Index: 7858120 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5727. Min Act: -0.1700
Data Index: 1669341 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5727. Min Act: -0.1700
Data Index: 2842062 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5727. Min Act: -0.1700
Data Index: 1425521 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5414. Min Act: -0.1700
Data Index: 5667657 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5414. Min Act: -0.1700
Data Index: 2382180 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.4789. Min Act: -0.1700
Data Index: 1996214 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5414. Min Act: -0.1699
Data Index: 936825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.5102. Min Act: -0.1700
Data Index: 6311521 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.4477. Min Act: -0.1700
Data Index: 1264811 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.4789. Min Act: -0.1699
Data Index: 5339963 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.4789. Min Act: -0.1700
Data Index: 3051750 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.4789. Min Act: -0.1700
Data Index: 2766099 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7602. Min Range: -6.7602
Max Act: 6.4789. Min Act: -0.1700
Data Index: 3964674 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19