Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 255 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.8537. Min Act: -0.1700
Data Index: 8310310 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.8378. Min Act: -0.1700
Data Index: 6098842 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.8378. Min Act: -0.1700
Data Index: 2204968 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.8219. Min Act: -0.1700
Data Index: 6313949 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.8059. Min Act: -0.1700
Data Index: 2877638 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7900. Min Act: -0.1700
Data Index: 6834405 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7900. Min Act: -0.1700
Data Index: 8455469 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7900. Min Act: -0.1700
Data Index: 4195902 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7741. Min Act: -0.1700
Data Index: 3434975 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7741. Min Act: -0.1700
Data Index: 2251301 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7581. Min Act: -0.1700
Data Index: 8822719 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7422. Min Act: -0.1700
Data Index: 1008602 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7581. Min Act: -0.1700
Data Index: 4516336 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7262. Min Act: -0.1700
Data Index: 2282194 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7422. Min Act: -0.1700
Data Index: 2071106 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7581. Min Act: -0.1700
Data Index: 4818 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7422. Min Act: -0.1700
Data Index: 1559575 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7422. Min Act: -0.1700
Data Index: 6705311 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7422. Min Act: -0.1700
Data Index: 1200238 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8537. Min Range: -2.8537
Max Act: 2.7262. Min Act: -0.1700
Data Index: 2588739 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19