Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5665 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.3355. Min Act: -0.1700
Data Index: 7572061 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.3043. Min Act: -0.1700
Data Index: 8511280 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2730. Min Act: -0.1700
Data Index: 2830726 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2730. Min Act: -0.1700
Data Index: 7045962 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2730. Min Act: -0.1700
Data Index: 3170746 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2730. Min Act: -0.1700
Data Index: 5828795 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2418. Min Act: -0.1700
Data Index: 8097732 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 5344351 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 830029 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 3335098 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1551557 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 5285066 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1926937 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 8235742 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1793. Min Act: -0.1700
Data Index: 4625749 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1793. Min Act: -0.1700
Data Index: 6022422 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1793. Min Act: -0.1700
Data Index: 867067 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1793. Min Act: -0.1700
Data Index: 1303552 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1793. Min Act: -0.1700
Data Index: 3352389 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1480. Min Act: -0.1700
Data Index: 7389955 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19