Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1516 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.3597. Min Act: -0.1700
Data Index: 2182778 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.3773. Min Act: -0.1700
Data Index: 5139022 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.3244. Min Act: -0.1700
Data Index: 4846185 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.3068. Min Act: -0.1700
Data Index: 5430900 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.3244. Min Act: -0.1700
Data Index: 5805056 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2891. Min Act: -0.1700
Data Index: 2165506 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.3068. Min Act: -0.1700
Data Index: 1252324 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2715. Min Act: -0.1700
Data Index: 6184023 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2715. Min Act: -0.1700
Data Index: 7222218 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2715. Min Act: -0.1700
Data Index: 7360391 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2539. Min Act: -0.1700
Data Index: 3607423 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2362. Min Act: -0.1700
Data Index: 1672958 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2362. Min Act: -0.1700
Data Index: 588785 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2362. Min Act: -0.1700
Data Index: 793246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2362. Min Act: -0.1700
Data Index: 624640 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2186. Min Act: -0.1700
Data Index: 746943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2010. Min Act: -0.1700
Data Index: 3067736 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2186. Min Act: -0.1700
Data Index: 1140277 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2186. Min Act: -0.1700
Data Index: 2659241 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3773. Min Range: -1.3773
Max Act: 1.2186. Min Act: -0.1700
Data Index: 2575891 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19