Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.9349. Min Act: -0.1700
Data Index: 5395388 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.6849. Min Act: -0.1700
Data Index: 172154 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5911. Min Act: -0.1700
Data Index: 8727216 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5911. Min Act: -0.1700
Data Index: 7324249 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5911. Min Act: -0.1700
Data Index: 3975500 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5599. Min Act: -0.1700
Data Index: 3677243 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5599. Min Act: -0.1700
Data Index: 8727222 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5286. Min Act: -0.1700
Data Index: 6557923 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.5286. Min Act: -0.1700
Data Index: 8724439 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4974. Min Act: -0.1700
Data Index: 8826065 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4661. Min Act: -0.1700
Data Index: 6348225 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4661. Min Act: -0.1700
Data Index: 8073673 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4349. Min Act: -0.1700
Data Index: 8440220 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4661. Min Act: -0.1700
Data Index: 2999217 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4349. Min Act: -0.1700
Data Index: 6247855 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4661. Min Act: -0.1700
Data Index: 3788692 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4349. Min Act: -0.1700
Data Index: 7430675 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7644130 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7855584 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9349. Min Range: -4.9349
Max Act: 4.4036. Min Act: -0.1700
Data Index: 4201834 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19