Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0574. Min Range: -5.0574
Max Act: 5.0574. Min Act: -0.1700
Data Index: 1763947 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.9636. Min Act: -0.1700
Data Index: 8064707 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.9636. Min Act: -0.1700
Data Index: 4413775 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.9636. Min Act: -0.1700
Data Index: 8587736 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.9324. Min Act: -0.1700
Data Index: 5441944 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.9324. Min Act: -0.1700
Data Index: 1314910 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.9011. Min Act: -0.1700
Data Index: 5510764 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.8699. Min Act: -0.1700
Data Index: 496149 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.8386. Min Act: -0.1700
Data Index: 8254013 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.8074. Min Act: -0.1700
Data Index: 1458256 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.8074. Min Act: -0.1700
Data Index: 5190201 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7761. Min Act: -0.1700
Data Index: 4454743 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7761. Min Act: -0.1700
Data Index: 4305740 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7449. Min Act: -0.1698
Data Index: 6888050 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7136. Min Act: -0.1700
Data Index: 778571 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7136. Min Act: -0.1700
Data Index: 2752205 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7136. Min Act: -0.1700
Data Index: 6474513 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1241833 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.7136. Min Act: -0.1700
Data Index: 5920345 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0574. Min Range: -5.0574
Max Act: 4.6511. Min Act: -0.1700
Data Index: 6550972 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19