Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2215 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.7105. Min Act: -0.1700
Data Index: 3435604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.7105. Min Act: -0.1700
Data Index: 1740967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 5476473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6792. Min Act: -0.1700
Data Index: 2724916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6792. Min Act: -0.1700
Data Index: 5068571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6792. Min Act: -0.1700
Data Index: 4850855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 5896090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 1150262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6480. Min Act: -0.1700
Data Index: 7902496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 8526118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 4780440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6806784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.5855. Min Act: -0.1700
Data Index: 5009097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6233173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 2011817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 705463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6072231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.5855. Min Act: -0.1700
Data Index: 3993344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.5855. Min Act: -0.1700
Data Index: 5184410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.5855. Min Act: -0.1700
Data Index: 5424851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19