Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.8632. Min Act: -0.1700
Data Index: 4505534 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.5507. Min Act: -0.1700
Data Index: 7455797 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.3944. Min Act: -0.1700
Data Index: 6141528 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.5194. Min Act: -0.1700
Data Index: 835844 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.4257. Min Act: -0.1700
Data Index: 4104119 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.4257. Min Act: -0.1700
Data Index: 2169358 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.3944. Min Act: -0.1700
Data Index: 2111215 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.3632. Min Act: -0.1700
Data Index: 2373391 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.3319. Min Act: -0.1700
Data Index: 6655073 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.2694. Min Act: -0.1700
Data Index: 3628507 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.1757. Min Act: -0.1700
Data Index: 7808517 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.2382. Min Act: -0.1700
Data Index: 1274006 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.2069. Min Act: -0.1700
Data Index: 4649614 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.1757. Min Act: -0.1700
Data Index: 5343234 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.1444. Min Act: -0.1700
Data Index: 4862196 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.1444. Min Act: -0.1700
Data Index: 7270739 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.1132. Min Act: -0.1700
Data Index: 6309417 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8632. Min Range: -7.8632
Max Act: 6.9569. Min Act: -0.1700
Data Index: 6014404 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.0194. Min Act: -0.1700
Data Index: 2948323 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8632. Min Range: -7.8632
Max Act: 7.1132. Min Act: -0.1700
Data Index: 7422642 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19