Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.4554. Min Act: -0.1700
Data Index: 4504155 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.4397. Min Act: -0.1700
Data Index: 3527825 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.4241. Min Act: -0.1700
Data Index: 1236398 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.4084. Min Act: -0.1700
Data Index: 4227003 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.4084. Min Act: -0.1700
Data Index: 5237638 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3770. Min Act: -0.1700
Data Index: 4537780 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3614. Min Act: -0.1700
Data Index: 909130 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3614. Min Act: -0.1700
Data Index: 2554776 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3300. Min Act: -0.1700
Data Index: 120733 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3300. Min Act: -0.1700
Data Index: 4854868 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3300. Min Act: -0.1700
Data Index: 7121144 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.3143. Min Act: -0.1700
Data Index: 7805048 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2986. Min Act: -0.1700
Data Index: 7447285 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2986. Min Act: -0.1700
Data Index: 2344339 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2829. Min Act: -0.1700
Data Index: 1673696 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2672. Min Act: -0.1700
Data Index: 101901 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2672. Min Act: -0.1700
Data Index: 2702006 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2515. Min Act: -0.1700
Data Index: 5379196 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2358. Min Act: -0.1700
Data Index: 5039581 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4554. Min Range: -3.4554
Max Act: 3.2358. Min Act: -0.1700
Data Index: 1753193 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19