Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6521. Min Act: -0.1700
Data Index: 1677322 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6521. Min Act: -0.1700
Data Index: 3429500 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6521. Min Act: -0.1700
Data Index: 3238683 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6521. Min Act: -0.1700
Data Index: 1709909 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6365. Min Act: -0.1700
Data Index: 2595490 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6365. Min Act: -0.1700
Data Index: 862007 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6365. Min Act: -0.1700
Data Index: 3366413 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6208. Min Act: -0.1700
Data Index: 6784294 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6208. Min Act: -0.1700
Data Index: 7631308 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6208. Min Act: -0.1700
Data Index: 8186388 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6052. Min Act: -0.1700
Data Index: 6646395 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6052. Min Act: -0.1700
Data Index: 3706505 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6052. Min Act: -0.1700
Data Index: 107834 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5895. Min Act: -0.1700
Data Index: 1296007 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5895. Min Act: -0.1700
Data Index: 76697 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5895. Min Act: -0.1700
Data Index: 1466998 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5895. Min Act: -0.1700
Data Index: 6031185 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5895. Min Act: -0.1700
Data Index: 3979791 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5895. Min Act: -0.1700
Data Index: 7769121 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.5739. Min Act: -0.1700
Data Index: 4838585 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19