Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.3625. Min Act: -0.1700
Data Index: 2128538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.2375. Min Act: -0.1700
Data Index: 3990461 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1437. Min Act: -0.1700
Data Index: 2937895 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1437. Min Act: -0.1700
Data Index: 723445 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1125. Min Act: -0.1700
Data Index: 5920210 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1125. Min Act: -0.1700
Data Index: 1408052 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1125. Min Act: -0.1700
Data Index: 6287072 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 2954305 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1125. Min Act: -0.1700
Data Index: 2654190 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 2015172 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0500. Min Act: -0.1700
Data Index: 4453390 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.1125. Min Act: -0.1700
Data Index: 1887591 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 3990079 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8345213 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 1898585 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 1362268 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0812. Min Act: -0.1700
Data Index: 2321764 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0500. Min Act: -0.1700
Data Index: 4432863 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0500. Min Act: -0.1700
Data Index: 2994466 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3625. Min Range: -6.3625
Max Act: 6.0500. Min Act: -0.1700
Data Index: 5880549 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19