Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1530 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.3144. Min Act: -0.1700
Data Index: 8735090 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1894. Min Act: -0.1700
Data Index: 7045086 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1894. Min Act: -0.1700
Data Index: 1984343 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1581. Min Act: -0.1700
Data Index: 2854693 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1581. Min Act: -0.1700
Data Index: 8059840 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1269. Min Act: -0.1700
Data Index: 1359017 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1269. Min Act: -0.1700
Data Index: 92336 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1269. Min Act: -0.1700
Data Index: 5962186 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0956. Min Act: -0.1700
Data Index: 8240397 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.1269. Min Act: -0.1700
Data Index: 110577 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0956. Min Act: -0.1700
Data Index: 3361098 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0956. Min Act: -0.1700
Data Index: 4130252 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0956. Min Act: -0.1700
Data Index: 6176869 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0644. Min Act: -0.1700
Data Index: 8292156 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0644. Min Act: -0.1700
Data Index: 7512804 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0644. Min Act: -0.1700
Data Index: 2515477 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0956. Min Act: -0.1700
Data Index: 7962374 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0644. Min Act: -0.1700
Data Index: 7161473 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0331. Min Act: -0.1700
Data Index: 5568167 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3144. Min Range: -5.3144
Max Act: 5.0644. Min Act: -0.1700
Data Index: 1738499 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19