Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.5300. Min Act: -0.1700
Data Index: 5707152 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2380929 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2800. Min Act: -0.1700
Data Index: 6642423 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2800. Min Act: -0.1700
Data Index: 2912432 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2487. Min Act: -0.1700
Data Index: 5918911 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2800. Min Act: -0.1700
Data Index: 3958018 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2487. Min Act: -0.1700
Data Index: 1652743 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2487. Min Act: -0.1700
Data Index: 2261203 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 159785 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 7439670 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3106585 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 1863919 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.2175. Min Act: -0.1700
Data Index: 5520588 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3820984 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 4276364 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 4285724 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5395473 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1550. Min Act: -0.1700
Data Index: 3466141 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5202814 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5300. Min Range: -5.5300
Max Act: 5.1862. Min Act: -0.1699
Data Index: 2650927 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19