Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1060 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.3676. Min Act: -0.1700
Data Index: 7511847 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.2426. Min Act: -0.1700
Data Index: 7498497 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.0864. Min Act: -0.1700
Data Index: 1644712 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9614. Min Act: -0.1700
Data Index: 2900405 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9301. Min Act: -0.1700
Data Index: 2824460 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 8601069 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 4619268 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8051. Min Act: -0.1700
Data Index: 4949589 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 5643488 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7739. Min Act: -0.1700
Data Index: 871739 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7114. Min Act: -0.1700
Data Index: 5467586 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7426. Min Act: -0.1700
Data Index: 4684399 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7739. Min Act: -0.1700
Data Index: 2879801 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7114. Min Act: -0.1700
Data Index: 5837712 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7426. Min Act: -0.1700
Data Index: 4774433 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.5864. Min Act: -0.1700
Data Index: 171998 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.6801. Min Act: -0.1700
Data Index: 3255658 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.6801. Min Act: -0.1700
Data Index: 1551237 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.6801. Min Act: -0.1700
Data Index: 5400647 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.6176. Min Act: -0.1700
Data Index: 4960852 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19