Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.9420. Min Act: -0.1700
Data Index: 6698391 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.8795. Min Act: -0.1700
Data Index: 5110004 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.8170. Min Act: -0.1700
Data Index: 2244138 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.7545. Min Act: -0.1700
Data Index: 8686807 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.6920. Min Act: -0.1700
Data Index: 151223 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.6920. Min Act: -0.1700
Data Index: 151221 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.6295. Min Act: -0.1700
Data Index: 2515005 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.6295. Min Act: -0.1700
Data Index: 7320423 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.5670. Min Act: -0.1700
Data Index: 2858891 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.5045. Min Act: -0.1700
Data Index: 1817130 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.5045. Min Act: -0.1700
Data Index: 3251437 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.5045. Min Act: -0.1700
Data Index: 2217587 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.4420. Min Act: -0.1700
Data Index: 8470042 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.4420. Min Act: -0.1700
Data Index: 4674186 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.4420. Min Act: -0.1700
Data Index: 5652796 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.4420. Min Act: -0.1700
Data Index: 4859250 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.4420. Min Act: -0.1700
Data Index: 1857251 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.4420. Min Act: -0.1700
Data Index: 1105539 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.3795. Min Act: -0.1700
Data Index: 5945143 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9420. Min Range: -8.9420
Max Act: 8.3170. Min Act: -0.1700
Data Index: 8113731 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19