Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.7558. Min Act: -0.1700
Data Index: 179273 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.7245. Min Act: -0.1700
Data Index: 3068000 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.6933. Min Act: -0.1700
Data Index: 6535325 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.6933. Min Act: -0.1700
Data Index: 4759519 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.6620. Min Act: -0.1700
Data Index: 3686675 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.6308. Min Act: -0.1700
Data Index: 8017302 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.6308. Min Act: -0.1700
Data Index: 46300 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5995. Min Act: -0.1700
Data Index: 6855310 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.6308. Min Act: -0.1700
Data Index: 526296 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5995. Min Act: -0.1700
Data Index: 1525493 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5683. Min Act: -0.1700
Data Index: 3089047 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5683. Min Act: -0.1700
Data Index: 5338788 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5683. Min Act: -0.1700
Data Index: 3257736 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5683. Min Act: -0.1700
Data Index: 8445882 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5370. Min Act: -0.1700
Data Index: 7530294 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5370. Min Act: -0.1700
Data Index: 3745962 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.4745. Min Act: -0.1700
Data Index: 5226536 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.5058. Min Act: -0.1700
Data Index: 4688878 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.4745. Min Act: -0.1700
Data Index: 2026129 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7558. Min Range: -4.7558
Max Act: 4.4745. Min Act: -0.1700
Data Index: 56810 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19