Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4333 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.3717. Min Act: -0.1700
Data Index: 1144311 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.3092. Min Act: -0.1700
Data Index: 6057576 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.2779. Min Act: -0.1700
Data Index: 3780756 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.2467. Min Act: -0.1700
Data Index: 2802231 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.2467. Min Act: -0.1700
Data Index: 2634861 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.2154. Min Act: -0.1700
Data Index: 2634867 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1842. Min Act: -0.1700
Data Index: 2401440 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1842. Min Act: -0.1700
Data Index: 2634865 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1529. Min Act: -0.1700
Data Index: 6497705 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1529. Min Act: -0.1700
Data Index: 2634853 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1529. Min Act: -0.1700
Data Index: 2634854 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1529. Min Act: -0.1700
Data Index: 2634862 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1529. Min Act: -0.1700
Data Index: 2634864 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1217. Min Act: -0.1700
Data Index: 6427548 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.1217. Min Act: -0.1700
Data Index: 2154376 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.0904. Min Act: -0.1700
Data Index: 7894835 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.0904. Min Act: -0.1700
Data Index: 5022227 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.0592. Min Act: -0.1700
Data Index: 2634866 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.0592. Min Act: -0.1700
Data Index: 5088827 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3717. Min Range: -5.3717
Max Act: 5.0279. Min Act: -0.1700
Data Index: 2634858 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19