Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.3954. Min Act: -0.1700
Data Index: 5934416 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.3017. Min Act: -0.1700
Data Index: 30796 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.3329. Min Act: -0.1700
Data Index: 6313264 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.2704. Min Act: -0.1700
Data Index: 8265354 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.2704. Min Act: -0.1700
Data Index: 5278855 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.2392. Min Act: -0.1700
Data Index: 7867797 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.2392. Min Act: -0.1700
Data Index: 6922942 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.2079. Min Act: -0.1700
Data Index: 3303100 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.2079. Min Act: -0.1700
Data Index: 7065239 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1767. Min Act: -0.1700
Data Index: 4193968 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1767. Min Act: -0.1700
Data Index: 2375058 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1454. Min Act: -0.1700
Data Index: 4298502 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1767. Min Act: -0.1700
Data Index: 6442282 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1767. Min Act: -0.1700
Data Index: 5278028 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1454. Min Act: -0.1700
Data Index: 7128211 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1454. Min Act: -0.1700
Data Index: 3136421 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1454. Min Act: -0.1700
Data Index: 7690686 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1142. Min Act: -0.1700
Data Index: 2965320 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1142. Min Act: -0.1700
Data Index: 4365625 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3954. Min Range: -5.3954
Max Act: 5.1142. Min Act: -0.1700
Data Index: 7367332 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19