Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0328. Min Range: -8.0328
Max Act: 8.0328. Min Act: -0.1700
Data Index: 1036159 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0328. Min Range: -8.0328
Max Act: 8.0328. Min Act: -0.1700
Data Index: 3886157 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.9703. Min Act: -0.1700
Data Index: 140915 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.9703. Min Act: -0.1700
Data Index: 2050642 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.7828. Min Act: -0.1700
Data Index: 2713657 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.6578. Min Act: -0.1700
Data Index: 6063391 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.6578. Min Act: -0.1700
Data Index: 255877 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.5953. Min Act: -0.1700
Data Index: 6203338 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.5953. Min Act: -0.1700
Data Index: 3623079 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.5328. Min Act: -0.1700
Data Index: 5296532 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4703. Min Act: -0.1700
Data Index: 1458896 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.5015. Min Act: -0.1700
Data Index: 2887240 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4703. Min Act: -0.1700
Data Index: 3923019 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4703. Min Act: -0.1700
Data Index: 7417047 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4703. Min Act: -0.1700
Data Index: 4941868 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.5015. Min Act: -0.1700
Data Index: 1073460 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4703. Min Act: -0.1700
Data Index: 254207 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4078. Min Act: -0.1700
Data Index: 3690148 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.4390. Min Act: -0.1700
Data Index: 4037335 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0328. Min Range: -8.0328
Max Act: 7.3453. Min Act: -0.1700
Data Index: 4548906 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19