Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6269 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.6173. Min Act: -0.1700
Data Index: 4884567 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.5235. Min Act: -0.1700
Data Index: 4550165 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.5235. Min Act: -0.1700
Data Index: 2205415 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.3048. Min Act: -0.1700
Data Index: 6937502 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.2423. Min Act: -0.1700
Data Index: 995629 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.1798. Min Act: -0.1700
Data Index: 537670 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.1798. Min Act: -0.1700
Data Index: 6149920 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.1798. Min Act: -0.1700
Data Index: 3968822 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.1173. Min Act: -0.1700
Data Index: 1423849 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.1173. Min Act: -0.1700
Data Index: 3896023 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6173. Min Range: -6.6173
Max Act: 6.0860. Min Act: -0.1700
Data Index: 1743618 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.9923. Min Act: -0.1700
Data Index: 4533934 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.9923. Min Act: -0.1700
Data Index: 2486539 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.9298. Min Act: -0.1700
Data Index: 942840 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 958650 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.9298. Min Act: -0.1700
Data Index: 4062300 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 5856722 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 4833406 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 2882838 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6173. Min Range: -6.6173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 5688109 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19