Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6370 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.9495. Min Act: -0.1700
Data Index: 7158555 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.9807. Min Act: -0.1700
Data Index: 4850300 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.7620. Min Act: -0.1700
Data Index: 3726436 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.6682. Min Act: -0.1700
Data Index: 3700986 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.6682. Min Act: -0.1700
Data Index: 4920688 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.6370. Min Act: -0.1700
Data Index: 5310357 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.6057. Min Act: -0.1700
Data Index: 1405477 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.6057. Min Act: -0.1700
Data Index: 1075865 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.5432. Min Act: -0.1700
Data Index: 393224 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.5120. Min Act: -0.1700
Data Index: 258713 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.5120. Min Act: -0.1700
Data Index: 2065536 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.5120. Min Act: -0.1700
Data Index: 551807 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.4807. Min Act: -0.1700
Data Index: 3475018 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.4807. Min Act: -0.1700
Data Index: 8694070 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.4182. Min Act: -0.1700
Data Index: 8536560 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.4495. Min Act: -0.1700
Data Index: 2977615 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.3870. Min Act: -0.1700
Data Index: 1680401 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.3870. Min Act: -0.1700
Data Index: 3891020 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.3870. Min Act: -0.1700
Data Index: 5082741 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9807. Min Range: -4.9807
Max Act: 4.3870. Min Act: -0.1700
Data Index: 4453004 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19