Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.5618. Min Act: -0.1700
Data Index: 5736777 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 8202173 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 7984290 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 6090017 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 6637314 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.5618. Min Act: -0.1700
Data Index: 7339186 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 6850752 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 6808136 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 806309 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 8653793 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 5495682 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 7539711 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 1219041 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 4597048 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 4585968 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 6771782 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 5821743 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 2345595 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4993. Min Act: -0.1700
Data Index: 2238508 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5618. Min Range: -8.5618
Max Act: 8.4368. Min Act: -0.1700
Data Index: 4506149 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19