Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5151 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.6244. Min Act: -0.1700
Data Index: 5352143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.5194. Min Act: -0.1700
Data Index: 6374226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.5194. Min Act: -0.1700
Data Index: 6134507 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.5370. Min Act: -0.1700
Data Index: 1027045 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4667. Min Act: -0.1700
Data Index: 2662113 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4843. Min Act: -0.1700
Data Index: 8531668 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4843. Min Act: -0.1700
Data Index: 7732637 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4667. Min Act: -0.1700
Data Index: 6970234 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4667. Min Act: -0.1700
Data Index: 5139887 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4667. Min Act: -0.1700
Data Index: 5220324 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4491. Min Act: -0.1700
Data Index: 5217267 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4491. Min Act: -0.1700
Data Index: 4795326 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4491. Min Act: -0.1700
Data Index: 2782343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4315. Min Act: -0.1700
Data Index: 3285094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4315. Min Act: -0.1700
Data Index: 810945 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4315. Min Act: -0.1700
Data Index: 3397050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4139. Min Act: -0.1700
Data Index: 1528774 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4315. Min Act: -0.1700
Data Index: 3821550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4491. Min Act: -0.1700
Data Index: 4048921 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6244. Min Range: -1.6244
Max Act: 1.4315. Min Act: -0.1700
Data Index: 1637441 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19