Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1622 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.4159. Min Act: -0.1700
Data Index: 3575204 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.3222. Min Act: -0.1700
Data Index: 1188836 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.3222. Min Act: -0.1700
Data Index: 3778619 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.3222. Min Act: -0.1700
Data Index: 8431175 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.3222. Min Act: -0.1700
Data Index: 3419391 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2909. Min Act: -0.1700
Data Index: 1454287 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2909. Min Act: -0.1700
Data Index: 854356 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2909. Min Act: -0.1700
Data Index: 4079508 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2909. Min Act: -0.1700
Data Index: 3539373 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 8771410 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2909. Min Act: -0.1700
Data Index: 3574094 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 8771434 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 7232040 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 6855047 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 6807529 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 1094668 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 3398894 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2597. Min Act: -0.1700
Data Index: 1457956 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2284. Min Act: -0.1700
Data Index: 2327108 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4159. Min Range: -4.4159
Max Act: 4.2284. Min Act: -0.1700
Data Index: 1419000 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19