Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4012. Min Range: -4.4012
Max Act: 4.4012. Min Act: -0.1700
Data Index: 4421617 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4012. Min Range: -4.4012
Max Act: 4.1512. Min Act: -0.1700
Data Index: 5033714 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4012. Min Range: -4.4012
Max Act: 4.1825. Min Act: -0.1700
Data Index: 4421615 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.9636. Min Act: -0.1700
Data Index: 12363 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.9949. Min Act: -0.1700
Data Index: 5383304 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.9324. Min Act: -0.1700
Data Index: 6701282 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.9011. Min Act: -0.1700
Data Index: 8710753 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.8699. Min Act: -0.1700
Data Index: 4935036 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4421622 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.9324. Min Act: -0.1700
Data Index: 6631282 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.8073. Min Act: -0.1700
Data Index: 574430 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7604. Min Act: -0.1700
Data Index: 8481508 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7604. Min Act: -0.1700
Data Index: 3036673 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7448. Min Act: -0.1700
Data Index: 4421611 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7604. Min Act: -0.1700
Data Index: 5659941 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.8073. Min Act: -0.1700
Data Index: 3877120 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7917. Min Act: -0.1700
Data Index: 8481504 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7135. Min Act: -0.1700
Data Index: 6099083 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.7291. Min Act: -0.1700
Data Index: 3054378 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4012. Min Range: -4.4012
Max Act: 3.6978. Min Act: -0.1700
Data Index: 374848 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19