Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.3358. Min Act: -0.1700
Data Index: 2270829 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.3358. Min Act: -0.1700
Data Index: 5062612 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.2420. Min Act: -0.1700
Data Index: 3348865 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.1795. Min Act: -0.1700
Data Index: 7040365 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.1483. Min Act: -0.1700
Data Index: 7217649 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.1170. Min Act: -0.1700
Data Index: 3265194 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.0858. Min Act: -0.1700
Data Index: 3045103 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.1170. Min Act: -0.1700
Data Index: 955728 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.0858. Min Act: -0.1700
Data Index: 6652734 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.0545. Min Act: -0.1700
Data Index: 4050519 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3358. Min Range: -5.3358
Max Act: 5.0233. Min Act: -0.1700
Data Index: 7492602 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.9608. Min Act: -0.1700
Data Index: 6214191 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.9920. Min Act: -0.1700
Data Index: 206692 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.9608. Min Act: -0.1700
Data Index: 6807820 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.9295. Min Act: -0.1700
Data Index: 1853586 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.8983. Min Act: -0.1700
Data Index: 4598985 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.9295. Min Act: -0.1700
Data Index: 1435360 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.8983. Min Act: -0.1700
Data Index: 3937210 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.8983. Min Act: -0.1700
Data Index: 8419825 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3358. Min Range: -5.3358
Max Act: 4.8983. Min Act: -0.1700
Data Index: 3590973 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19