Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.2919. Min Act: -0.1700
Data Index: 2292239 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1982. Min Act: -0.1700
Data Index: 691875 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1982. Min Act: -0.1700
Data Index: 7336528 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1357. Min Act: -0.1700
Data Index: 666818 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1357. Min Act: -0.1700
Data Index: 4300873 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1915039 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1044. Min Act: -0.1700
Data Index: 750955 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.1044. Min Act: -0.1700
Data Index: 1712703 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0732. Min Act: -0.1700
Data Index: 2191977 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0732. Min Act: -0.1700
Data Index: 733265 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0107. Min Act: -0.1700
Data Index: 5520950 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.0107. Min Act: -0.1700
Data Index: 5331428 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 2892978 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 1313829 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 2569616 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 3602361 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 6729085 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 3519940 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 125176 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9482. Min Act: -0.1700
Data Index: 988212 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19