Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.9048. Min Act: -0.1700
Data Index: 2662001 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.8423. Min Act: -0.1700
Data Index: 3153274 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.7173. Min Act: -0.1700
Data Index: 2765175 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.5923. Min Act: -0.1700
Data Index: 193927 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.5923. Min Act: -0.1700
Data Index: 2997126 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.5923. Min Act: -0.1700
Data Index: 6173881 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.5298. Min Act: -0.1700
Data Index: 3443040 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 5652098 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 878794 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 1127090 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 2257476 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 6177041 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 2856559 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.3423. Min Act: -0.1700
Data Index: 6280633 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 1673388 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.3423. Min Act: -0.1700
Data Index: 2922193 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.3423. Min Act: -0.1700
Data Index: 5295502 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 811009 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.3423. Min Act: -0.1700
Data Index: 641779 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9048. Min Range: -8.9048
Max Act: 8.3423. Min Act: -0.1700
Data Index: 3704770 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19