Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6710. Min Range: -6.6710
Max Act: 6.6710. Min Act: -0.1700
Data Index: 3674785 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6710. Min Range: -6.6710
Max Act: 6.3898. Min Act: -0.1700
Data Index: 576854 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6710. Min Range: -6.6710
Max Act: 6.1398. Min Act: -0.1700
Data Index: 8160748 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6710. Min Range: -6.6710
Max Act: 6.1085. Min Act: -0.1700
Data Index: 5606628 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6710. Min Range: -6.6710
Max Act: 6.0773. Min Act: -0.1700
Data Index: 2597283 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6710. Min Range: -6.6710
Max Act: 6.0460. Min Act: -0.1700
Data Index: 322402 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.9523. Min Act: -0.1700
Data Index: 8054004 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.9210. Min Act: -0.1700
Data Index: 2014950 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.8898. Min Act: -0.1700
Data Index: 7560688 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.8898. Min Act: -0.1700
Data Index: 4804643 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.8273. Min Act: -0.1700
Data Index: 6448099 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7960. Min Act: -0.1700
Data Index: 1335110 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7960. Min Act: -0.1700
Data Index: 6291908 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7960. Min Act: -0.1700
Data Index: 4400645 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7960. Min Act: -0.1700
Data Index: 8000021 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7648. Min Act: -0.1700
Data Index: 154895 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7648. Min Act: -0.1700
Data Index: 8669068 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7648. Min Act: -0.1700
Data Index: 146834 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7335. Min Act: -0.1700
Data Index: 5049045 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6710. Min Range: -6.6710
Max Act: 5.7648. Min Act: -0.1700
Data Index: 5071790 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19