Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3932 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0703. Min Act: -0.1700
Data Index: 8221527 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0391. Min Act: -0.1700
Data Index: 5222096 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9141. Min Act: -0.1700
Data Index: 638655 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9141. Min Act: -0.1700
Data Index: 2660150 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9141. Min Act: -0.1700
Data Index: 2660148 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 7315086 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.7891. Min Act: -0.1700
Data Index: 2697282 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.7891. Min Act: -0.1700
Data Index: 8506417 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.7578. Min Act: -0.1700
Data Index: 1161365 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.7266. Min Act: -0.1700
Data Index: 5623804 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.7266. Min Act: -0.1700
Data Index: 3300511 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.7266. Min Act: -0.1700
Data Index: 7315087 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6953. Min Act: -0.1700
Data Index: 5750270 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6641. Min Act: -0.1700
Data Index: 8280628 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6328. Min Act: -0.1700
Data Index: 5973018 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6328. Min Act: -0.1700
Data Index: 4016487 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6328. Min Act: -0.1700
Data Index: 1760491 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6328. Min Act: -0.1700
Data Index: 7367376 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6016. Min Act: -0.1700
Data Index: 2688308 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.6016. Min Act: -0.1700
Data Index: 3277695 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19