Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.6339. Min Act: -0.1700
Data Index: 1785664 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.6182. Min Act: -0.1700
Data Index: 1528391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.6182. Min Act: -0.1700
Data Index: 8197571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.5713. Min Act: -0.1700
Data Index: 5708404 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.5400. Min Act: -0.1700
Data Index: 6204279 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.5086. Min Act: -0.1700
Data Index: 4018867 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4773. Min Act: -0.1700
Data Index: 501802 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4773. Min Act: -0.1700
Data Index: 4404863 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4773. Min Act: -0.1700
Data Index: 299411 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4773. Min Act: -0.1700
Data Index: 3223431 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4617. Min Act: -0.1700
Data Index: 7895150 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4460. Min Act: -0.1700
Data Index: 984643 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4617. Min Act: -0.1700
Data Index: 6104499 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4460. Min Act: -0.1700
Data Index: 5359183 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4773. Min Act: -0.1700
Data Index: 4824301 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4617. Min Act: -0.1700
Data Index: 145298 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4303. Min Act: -0.1700
Data Index: 5886516 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4146. Min Act: -0.1700
Data Index: 5345798 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4460. Min Act: -0.1700
Data Index: 1887566 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6339. Min Range: -3.6339
Max Act: 3.4146. Min Act: -0.1700
Data Index: 4706650 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19