Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2683. Min Act: -0.1700
Data Index: 4087910 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2517. Min Act: -0.1700
Data Index: 6801205 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2517. Min Act: -0.1700
Data Index: 7581577 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2517. Min Act: -0.1700
Data Index: 3013603 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 983850 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2352. Min Act: -0.1700
Data Index: 5084189 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2352. Min Act: -0.1700
Data Index: 6394924 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 1344278 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2352. Min Act: -0.1700
Data Index: 2156122 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2352. Min Act: -0.1700
Data Index: 4532980 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 2443247 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 1642316 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1698
Data Index: 3256246 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 3530987 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 778234 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 475001 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2021. Min Act: -0.1700
Data Index: 5023016 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2187. Min Act: -0.1700
Data Index: 616789 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2021. Min Act: -0.1700
Data Index: 1960256 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2683. Min Range: -2.2683
Max Act: 2.2021. Min Act: -0.1700
Data Index: 6939910 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19