Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.4935. Min Act: -0.1700
Data Index: 1675681 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.4310. Min Act: -0.1700
Data Index: 2644864 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.3998. Min Act: -0.1700
Data Index: 830108 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.3998. Min Act: -0.1700
Data Index: 4779596 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.3373. Min Act: -0.1700
Data Index: 7356851 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.1185. Min Act: -0.1700
Data Index: 4918514 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.0873. Min Act: -0.1700
Data Index: 4822866 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4935. Min Range: -7.4935
Max Act: 7.0560. Min Act: -0.1700
Data Index: 5519172 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9935. Min Act: -0.1700
Data Index: 4495538 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9935. Min Act: -0.1700
Data Index: 2856379 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9935. Min Act: -0.1700
Data Index: 5851913 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9935. Min Act: -0.1700
Data Index: 4362355 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9935. Min Act: -0.1700
Data Index: 7085795 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9623. Min Act: -0.1700
Data Index: 2689996 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9310. Min Act: -0.1700
Data Index: 6672139 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.9310. Min Act: -0.1700
Data Index: 2168299 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.8998. Min Act: -0.1700
Data Index: 6591648 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.8685. Min Act: -0.1700
Data Index: 4174341 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.8998. Min Act: -0.1700
Data Index: 5851856 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4935. Min Range: -7.4935
Max Act: 6.8998. Min Act: -0.1700
Data Index: 5209631 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19