Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.2765. Min Act: -0.1700
Data Index: 3860899 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.2453. Min Act: -0.1700
Data Index: 338315 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.2140. Min Act: -0.1700
Data Index: 6762727 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.2140. Min Act: -0.1700
Data Index: 6789314 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.2140. Min Act: -0.1700
Data Index: 2054741 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1828. Min Act: -0.1700
Data Index: 155301 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1515. Min Act: -0.1700
Data Index: 1411983 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1515. Min Act: -0.1700
Data Index: 7740919 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1203. Min Act: -0.1700
Data Index: 6248337 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1515. Min Act: -0.1700
Data Index: 2337448 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1515. Min Act: -0.1700
Data Index: 5866916 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1515. Min Act: -0.1700
Data Index: 8762078 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1203. Min Act: -0.1700
Data Index: 1800445 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1203. Min Act: -0.1700
Data Index: 1149977 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1203. Min Act: -0.1700
Data Index: 4413231 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.1203. Min Act: -0.1700
Data Index: 1507884 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 3966642 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 2254172 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0890. Min Act: -0.1700
Data Index: 5775377 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2765. Min Range: -5.2765
Max Act: 5.0578. Min Act: -0.1700
Data Index: 1671094 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19