Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2730. Min Act: -0.1700
Data Index: 5214062 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2105. Min Act: -0.1700
Data Index: 37926 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2105. Min Act: -0.1700
Data Index: 7240332 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1792. Min Act: -0.1700
Data Index: 846807 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1792. Min Act: -0.1700
Data Index: 3599179 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2434154 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1167. Min Act: -0.1700
Data Index: 7632038 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1480. Min Act: -0.1700
Data Index: 8246002 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1167. Min Act: -0.1700
Data Index: 5160201 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0855. Min Act: -0.1700
Data Index: 915075 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1167. Min Act: -0.1700
Data Index: 3104184 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2203888 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0542. Min Act: -0.1700
Data Index: 2708921 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0230. Min Act: -0.1700
Data Index: 6579199 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1687629 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4235475 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9917. Min Act: -0.1700
Data Index: 915078 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9605. Min Act: -0.1700
Data Index: 4606079 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9605. Min Act: -0.1700
Data Index: 5286700 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3329017 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19