Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.2151. Min Act: -0.1700
Data Index: 2732539 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1839. Min Act: -0.1700
Data Index: 3772575 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1839. Min Act: -0.1700
Data Index: 6837556 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1526. Min Act: -0.1700
Data Index: 4888112 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1213. Min Act: -0.1700
Data Index: 4573733 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0901. Min Act: -0.1700
Data Index: 7405069 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1213. Min Act: -0.1700
Data Index: 4900919 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1213. Min Act: -0.1700
Data Index: 2962345 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.1213. Min Act: -0.1700
Data Index: 4735734 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0901. Min Act: -0.1700
Data Index: 1668198 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0901. Min Act: -0.1700
Data Index: 7402763 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 2838485 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 7138604 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 7136895 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 6532719 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 5853884 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 2762686 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 479103 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 3516667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2151. Min Range: -4.2151
Max Act: 4.0588. Min Act: -0.1700
Data Index: 4474738 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19