Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.2013. Min Act: -0.1700
Data Index: 1208080 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.1388. Min Act: -0.1700
Data Index: 5813581 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.1076. Min Act: -0.1700
Data Index: 2129928 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.1076. Min Act: -0.1700
Data Index: 2020818 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.1076. Min Act: -0.1700
Data Index: 902077 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.0763. Min Act: -0.1700
Data Index: 2673571 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.0138. Min Act: -0.1700
Data Index: 3252459 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2013. Min Range: -4.2013
Max Act: 4.0138. Min Act: -0.1700
Data Index: 1744762 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9513. Min Act: -0.1700
Data Index: 209320 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9356. Min Act: -0.1700
Data Index: 8728238 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9513. Min Act: -0.1700
Data Index: 7562868 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9513. Min Act: -0.1700
Data Index: 5038257 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9356. Min Act: -0.1700
Data Index: 1819242 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9200. Min Act: -0.1700
Data Index: 4858386 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9356. Min Act: -0.1700
Data Index: 442397 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9200. Min Act: -0.1700
Data Index: 7017041 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.8887. Min Act: -0.1700
Data Index: 6422405 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.9044. Min Act: -0.1700
Data Index: 4019299 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.8731. Min Act: -0.1700
Data Index: 914465 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2013. Min Range: -4.2013
Max Act: 3.8887. Min Act: -0.1700
Data Index: 6939532 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19