Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1592 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9218. Min Range: -6.9218
Max Act: 6.9218. Min Act: -0.1700
Data Index: 3673260 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9218. Min Range: -6.9218
Max Act: 6.0156. Min Act: -0.1700
Data Index: 5873742 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6620097 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.9531. Min Act: -0.1700
Data Index: 4593889 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.8593. Min Act: -0.1700
Data Index: 2687826 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.8593. Min Act: -0.1700
Data Index: 8352953 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.7968. Min Act: -0.1700
Data Index: 8819878 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.7968. Min Act: -0.1700
Data Index: 8296632 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.7968. Min Act: -0.1700
Data Index: 6509917 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.7656. Min Act: -0.1700
Data Index: 5873741 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.7656. Min Act: -0.1700
Data Index: 5873739 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.6406. Min Act: -0.1700
Data Index: 4438427 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.5468. Min Act: -0.1700
Data Index: 8108343 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.5781. Min Act: -0.1700
Data Index: 1206672 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.6093. Min Act: -0.1700
Data Index: 623554 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.5156. Min Act: -0.1700
Data Index: 398996 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.5781. Min Act: -0.1700
Data Index: 8504215 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.3906. Min Act: -0.1700
Data Index: 6095024 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.4843. Min Act: -0.1700
Data Index: 4137308 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9218. Min Range: -6.9218
Max Act: 5.3593. Min Act: -0.1700
Data Index: 7027474 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19