Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4794 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.7061. Min Act: -0.1700
Data Index: 863722 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.4248. Min Act: -0.1700
Data Index: 1228743 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.4248. Min Act: -0.1700
Data Index: 3220523 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.3936. Min Act: -0.1700
Data Index: 1117364 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.3311. Min Act: -0.1700
Data Index: 663598 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2998. Min Act: -0.1700
Data Index: 4933777 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.3311. Min Act: -0.1700
Data Index: 1817457 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2686. Min Act: -0.1700
Data Index: 1631876 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2686. Min Act: -0.1700
Data Index: 1712519 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2061. Min Act: -0.1700
Data Index: 185765 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2373. Min Act: -0.1700
Data Index: 2324922 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2061. Min Act: -0.1700
Data Index: 3949273 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2061. Min Act: -0.1700
Data Index: 6861177 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.2061. Min Act: -0.1700
Data Index: 8598888 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.1436. Min Act: -0.1700
Data Index: 6260895 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.1748. Min Act: -0.1700
Data Index: 8219940 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.1436. Min Act: -0.1700
Data Index: 245415 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.0811. Min Act: -0.1700
Data Index: 1853613 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.1123. Min Act: -0.1700
Data Index: 6590117 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7061. Min Range: -5.7061
Max Act: 5.1123. Min Act: -0.1700
Data Index: 1128443 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19