Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 383 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6616. Min Act: -0.1700
Data Index: 2465147 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6303. Min Act: -0.1700
Data Index: 6398735 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6303. Min Act: -0.1700
Data Index: 3729873 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5990. Min Act: -0.1700
Data Index: 27131 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5990. Min Act: -0.1700
Data Index: 6547679 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.6303. Min Act: -0.1700
Data Index: 5948997 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5677. Min Act: -0.1700
Data Index: 5253094 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5677. Min Act: -0.1700
Data Index: 7347979 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5207. Min Act: -0.1700
Data Index: 1001321 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.5051. Min Act: -0.1700
Data Index: 5027146 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4737. Min Act: -0.1700
Data Index: 8065231 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4894. Min Act: -0.1700
Data Index: 4809255 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4737. Min Act: -0.1700
Data Index: 7225028 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4737. Min Act: -0.1700
Data Index: 1262178 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 2627571 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 122531 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4737. Min Act: -0.1700
Data Index: 3068525 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 354367 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4581. Min Act: -0.1700
Data Index: 3397150 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6616. Min Range: -3.6616
Max Act: 3.4424. Min Act: -0.1700
Data Index: 4809254 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19