Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.3222. Min Act: -0.1700
Data Index: 1950612 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.3222. Min Act: -0.1700
Data Index: 2054221 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.3222. Min Act: -0.1700
Data Index: 2054218 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.2910. Min Act: -0.1700
Data Index: 8050127 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.2597. Min Act: -0.1700
Data Index: 2601014 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.2597. Min Act: -0.1700
Data Index: 1342650 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.2285. Min Act: -0.1700
Data Index: 5771207 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1972. Min Act: -0.1700
Data Index: 5215943 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1972. Min Act: -0.1700
Data Index: 1465287 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1972. Min Act: -0.1700
Data Index: 7045910 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1660. Min Act: -0.1700
Data Index: 7504758 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1660. Min Act: -0.1700
Data Index: 1479875 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1347. Min Act: -0.1700
Data Index: 7746072 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1660. Min Act: -0.1700
Data Index: 7504756 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1347. Min Act: -0.1700
Data Index: 3618014 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1660. Min Act: -0.1700
Data Index: 3579915 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1347. Min Act: -0.1700
Data Index: 5605459 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1035. Min Act: -0.1700
Data Index: 6792454 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1347. Min Act: -0.1700
Data Index: 1887553 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3222. Min Range: -5.3222
Max Act: 5.1347. Min Act: -0.1700
Data Index: 2663752 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19