Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.8044. Min Act: -0.1700
Data Index: 3097303 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.7419. Min Act: -0.1700
Data Index: 183233 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5446096 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.7107. Min Act: -0.1700
Data Index: 6021738 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.6794. Min Act: -0.1700
Data Index: 4820993 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5544. Min Act: -0.1700
Data Index: 6261064 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.6169. Min Act: -0.1700
Data Index: 1969139 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5544. Min Act: -0.1700
Data Index: 6564597 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5857. Min Act: -0.1700
Data Index: 319533 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.6169. Min Act: -0.1700
Data Index: 1428582 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5857. Min Act: -0.1700
Data Index: 829903 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5544. Min Act: -0.1700
Data Index: 2206739 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5544. Min Act: -0.1700
Data Index: 1271936 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.6169. Min Act: -0.1700
Data Index: 4768642 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5544. Min Act: -0.1700
Data Index: 3525861 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5544. Min Act: -0.1700
Data Index: 4328069 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5232. Min Act: -0.1700
Data Index: 5433864 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5232. Min Act: -0.1700
Data Index: 548864 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.4919. Min Act: -0.1700
Data Index: 4040658 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8044. Min Range: -4.8044
Max Act: 4.5232. Min Act: -0.1700
Data Index: 4793976 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19