Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.2218. Min Act: -0.1700
Data Index: 2050258 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.2060. Min Act: -0.1700
Data Index: 2354258 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.2060. Min Act: -0.1700
Data Index: 4984327 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.1431. Min Act: -0.1700
Data Index: 1611079 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.1431. Min Act: -0.1700
Data Index: 7329725 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.1274. Min Act: -0.1700
Data Index: 2050267 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.0958. Min Act: -0.1700
Data Index: 4769734 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.0643. Min Act: -0.1700
Data Index: 5502834 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.0643. Min Act: -0.1700
Data Index: 2050261 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.0327. Min Act: -0.1700
Data Index: 6818180 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9853. Min Act: -0.1700
Data Index: 4403109 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.0011. Min Act: -0.1700
Data Index: 8287860 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2218. Min Range: -3.2218
Max Act: 3.0011. Min Act: -0.1700
Data Index: 4750028 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9695. Min Act: -0.1700
Data Index: 7829188 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9853. Min Act: -0.1700
Data Index: 5207768 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9853. Min Act: -0.1700
Data Index: 3944018 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9537. Min Act: -0.1700
Data Index: 8525990 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9853. Min Act: -0.1700
Data Index: 2669060 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9695. Min Act: -0.1700
Data Index: 1373100 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2218. Min Range: -3.2218
Max Act: 2.9537. Min Act: -0.1700
Data Index: 2097210 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19