Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7968. Min Act: -0.1700
Data Index: 7955914 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7968. Min Act: -0.1700
Data Index: 6204789 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7656. Min Act: -0.1700
Data Index: 8479888 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7031. Min Act: -0.1700
Data Index: 1418273 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7031. Min Act: -0.1700
Data Index: 7004744 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7343. Min Act: -0.1700
Data Index: 4526243 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6718. Min Act: -0.1700
Data Index: 1418268 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6718. Min Act: -0.1700
Data Index: 8826048 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 5348001 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7031. Min Act: -0.1700
Data Index: 700167 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4146157 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7031. Min Act: -0.1700
Data Index: 3775124 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6093. Min Act: -0.1700
Data Index: 2164446 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6093. Min Act: -0.1699
Data Index: 4400999 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6093. Min Act: -0.1700
Data Index: 2230039 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 6204785 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 3253167 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 3401219 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4834727 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4658898 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19