Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1811 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0092. Min Range: -5.0092
Max Act: 5.0092. Min Act: -0.1700
Data Index: 7129704 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7279. Min Act: -0.1700
Data Index: 2212705 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6342. Min Act: -0.1700
Data Index: 6538933 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6654. Min Act: -0.1700
Data Index: 4205320 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6342. Min Act: -0.1700
Data Index: 2470370 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6029. Min Act: -0.1700
Data Index: 3036099 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.6029. Min Act: -0.1700
Data Index: 4902660 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5404. Min Act: -0.1700
Data Index: 807312 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5092. Min Act: -0.1700
Data Index: 2337586 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4779. Min Act: -0.1700
Data Index: 8368740 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.5092. Min Act: -0.1700
Data Index: 4297918 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4779. Min Act: -0.1700
Data Index: 2938716 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4779. Min Act: -0.1700
Data Index: 7473086 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4467. Min Act: -0.1700
Data Index: 3738169 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4779. Min Act: -0.1700
Data Index: 2626405 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4779. Min Act: -0.1700
Data Index: 702893 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4779. Min Act: -0.1700
Data Index: 1625505 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4467. Min Act: -0.1700
Data Index: 1942678 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4467. Min Act: -0.1700
Data Index: 6321955 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.4467. Min Act: -0.1700
Data Index: 8117428 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19