Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0604. Min Range: -6.0604
Max Act: 6.0604. Min Act: -0.1700
Data Index: 4161158 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.8104. Min Act: -0.1700
Data Index: 3234862 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.8104. Min Act: -0.1700
Data Index: 3580552 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.7167. Min Act: -0.1700
Data Index: 231278 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.6854. Min Act: -0.1700
Data Index: 1770401 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.6854. Min Act: -0.1700
Data Index: 5680061 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.6854. Min Act: -0.1700
Data Index: 8032121 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5917. Min Act: -0.1700
Data Index: 4904546 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5917. Min Act: -0.1700
Data Index: 1821019 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.6229. Min Act: -0.1700
Data Index: 2060221 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5917. Min Act: -0.1700
Data Index: 4807758 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5604. Min Act: -0.1700
Data Index: 393732 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5604. Min Act: -0.1700
Data Index: 3542512 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5604. Min Act: -0.1700
Data Index: 8168256 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5292. Min Act: -0.1700
Data Index: 2732915 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.4979. Min Act: -0.1700
Data Index: 1207862 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.5292. Min Act: -0.1700
Data Index: 1151948 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.4667. Min Act: -0.1700
Data Index: 5804550 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.4667. Min Act: -0.1700
Data Index: 465249 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0604. Min Range: -6.0604
Max Act: 5.4667. Min Act: -0.1700
Data Index: 5410908 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19