Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1328. Min Range: -5.1328
Max Act: 5.1328. Min Act: -0.1700
Data Index: 5013473 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1328. Min Range: -5.1328
Max Act: 5.1015. Min Act: -0.1700
Data Index: 7574459 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1328. Min Range: -5.1328
Max Act: 5.0703. Min Act: -0.1700
Data Index: 4560198 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1328. Min Range: -5.1328
Max Act: 5.0390. Min Act: -0.1700
Data Index: 638671 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1328. Min Range: -5.1328
Max Act: 5.0078. Min Act: -0.1700
Data Index: 5121356 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.9765. Min Act: -0.1700
Data Index: 585321 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.9453. Min Act: -0.1700
Data Index: 6024913 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.9140. Min Act: -0.1700
Data Index: 6147050 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.9140. Min Act: -0.1700
Data Index: 6400234 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.8828. Min Act: -0.1700
Data Index: 1613209 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.8203. Min Act: -0.1700
Data Index: 5825636 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.8515. Min Act: -0.1700
Data Index: 7336962 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.8203. Min Act: -0.1700
Data Index: 3126295 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.8203. Min Act: -0.1700
Data Index: 3229587 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.8203. Min Act: -0.1700
Data Index: 2978385 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.7890. Min Act: -0.1700
Data Index: 4960773 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.7890. Min Act: -0.1700
Data Index: 2742979 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.7890. Min Act: -0.1700
Data Index: 4665069 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.7890. Min Act: -0.1700
Data Index: 6251713 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1328. Min Range: -5.1328
Max Act: 4.7578. Min Act: -0.1700
Data Index: 2302264 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19