Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.3265. Min Act: -0.1700
Data Index: 7747119 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.2015. Min Act: -0.1700
Data Index: 5198300 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.1703. Min Act: -0.1700
Data Index: 581276 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.1703. Min Act: -0.1700
Data Index: 3552063 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8242623 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.1078. Min Act: -0.1700
Data Index: 7802227 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0140. Min Act: -0.1700
Data Index: 6913029 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0453. Min Act: -0.1700
Data Index: 1391781 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0765. Min Act: -0.1700
Data Index: 3946748 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0453. Min Act: -0.1700
Data Index: 4688542 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0453. Min Act: -0.1700
Data Index: 1851309 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0453. Min Act: -0.1700
Data Index: 3075987 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0140. Min Act: -0.1700
Data Index: 4672358 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0140. Min Act: -0.1700
Data Index: 7480496 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0140. Min Act: -0.1700
Data Index: 548474 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0140. Min Act: -0.1700
Data Index: 7168894 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3265. Min Range: -5.3265
Max Act: 4.9828. Min Act: -0.1700
Data Index: 7857987 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3265. Min Range: -5.3265
Max Act: 4.9515. Min Act: -0.1700
Data Index: 7927466 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3265. Min Range: -5.3265
Max Act: 5.0140. Min Act: -0.1700
Data Index: 4099161 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3265. Min Range: -5.3265
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1394867 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19