Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.6588. Min Act: -0.1700
Data Index: 8429097 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.5180. Min Act: -0.1700
Data Index: 3543925 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.3926. Min Act: -0.1700
Data Index: 4048649 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.4083. Min Act: -0.1700
Data Index: 1578394 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.3456. Min Act: -0.1700
Data Index: 7449278 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.3456. Min Act: -0.1700
Data Index: 908555 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.3456. Min Act: -0.1700
Data Index: 839159 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2985. Min Act: -0.1700
Data Index: 4622392 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.3142. Min Act: -0.1700
Data Index: 6030069 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.3299. Min Act: -0.1700
Data Index: 7878348 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2828. Min Act: -0.1700
Data Index: 6719262 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2985. Min Act: -0.1700
Data Index: 4626654 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2671. Min Act: -0.1700
Data Index: 6779182 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2671. Min Act: -0.1700
Data Index: 4148159 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2357. Min Act: -0.1700
Data Index: 6178764 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2671. Min Act: -0.1700
Data Index: 5630078 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2514. Min Act: -0.1700
Data Index: 783374 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2671. Min Act: -0.1700
Data Index: 1458609 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2514. Min Act: -0.1700
Data Index: 7151340 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6588. Min Range: -3.6588
Max Act: 3.2514. Min Act: -0.1700
Data Index: 499661 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19