Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.9196. Min Act: -0.1700
Data Index: 5094049 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.7946. Min Act: -0.1700
Data Index: 5094046 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.6696. Min Act: -0.1700
Data Index: 5094050 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.5446. Min Act: -0.1700
Data Index: 5094052 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.5446. Min Act: -0.1700
Data Index: 1804335 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.4196. Min Act: -0.1700
Data Index: 7915505 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.4196. Min Act: -0.1700
Data Index: 909960 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.2946. Min Act: -0.1700
Data Index: 2150798 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.2946. Min Act: -0.1700
Data Index: 7355012 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.2946. Min Act: -0.1700
Data Index: 4511103 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.2946. Min Act: -0.1700
Data Index: 4377544 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.2946. Min Act: -0.1700
Data Index: 5645227 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.1696. Min Act: -0.1700
Data Index: 8131147 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.1696. Min Act: -0.1700
Data Index: 6684121 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.1696. Min Act: -0.1700
Data Index: 6991847 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.1696. Min Act: -0.1700
Data Index: 8131148 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.1696. Min Act: -0.1700
Data Index: 2909532 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.0446. Min Act: -0.1700
Data Index: 5094044 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.0446. Min Act: -0.1700
Data Index: 717507 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.9196. Min Range: -20.9196
Max Act: 20.0446. Min Act: -0.1700
Data Index: 953378 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19