Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5354 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.2167. Min Act: -0.1700
Data Index: 6620430 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.2167. Min Act: -0.1700
Data Index: 8330138 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.0917. Min Act: -0.1700
Data Index: 4077454 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.1230. Min Act: -0.1700
Data Index: 6769891 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.1230. Min Act: -0.1700
Data Index: 836824 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.0605. Min Act: -0.1700
Data Index: 60533 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3186112 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2167. Min Range: -7.2167
Max Act: 7.0292. Min Act: -0.1700
Data Index: 1919374 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.9980. Min Act: -0.1700
Data Index: 2550893 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.9667. Min Act: -0.1700
Data Index: 3665199 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.9355. Min Act: -0.1700
Data Index: 4375345 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.9042. Min Act: -0.1700
Data Index: 8042031 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.8417. Min Act: -0.1700
Data Index: 2880800 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.8417. Min Act: -0.1700
Data Index: 405770 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.8730. Min Act: -0.1700
Data Index: 5226685 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.8417. Min Act: -0.1700
Data Index: 1331249 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.7792. Min Act: -0.1700
Data Index: 7623999 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.7792. Min Act: -0.1700
Data Index: 5459852 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.7792. Min Act: -0.1700
Data Index: 4546446 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2167. Min Range: -7.2167
Max Act: 6.7480. Min Act: -0.1700
Data Index: 7312697 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19