Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.3619. Min Act: -0.1700
Data Index: 5522104 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.3619. Min Act: -0.1700
Data Index: 4628721 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.2994. Min Act: -0.1700
Data Index: 812037 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.3306. Min Act: -0.1700
Data Index: 5068760 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.2681. Min Act: -0.1700
Data Index: 7567854 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.2994. Min Act: -0.1700
Data Index: 2758097 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.2681. Min Act: -0.1700
Data Index: 56314 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.2056. Min Act: -0.1700
Data Index: 1687589 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1744. Min Act: -0.1700
Data Index: 7908140 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1744. Min Act: -0.1700
Data Index: 5954776 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1744. Min Act: -0.1700
Data Index: 6702105 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1431. Min Act: -0.1700
Data Index: 4840326 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1118. Min Act: -0.1700
Data Index: 4840327 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1118. Min Act: -0.1700
Data Index: 3905034 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1118. Min Act: -0.1700
Data Index: 165146 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.1118. Min Act: -0.1700
Data Index: 2678060 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.0806. Min Act: -0.1700
Data Index: 6795566 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.0806. Min Act: -0.1700
Data Index: 616857 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.0806. Min Act: -0.1700
Data Index: 5454086 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3619. Min Range: -4.3619
Max Act: 4.0806. Min Act: -0.1700
Data Index: 4117374 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19