Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6074 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.5609. Min Act: -0.1700
Data Index: 6281847 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.8734. Min Act: -0.1700
Data Index: 5951142 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.6859. Min Act: -0.1700
Data Index: 8430253 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.6859. Min Act: -0.1700
Data Index: 3602901 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.6859. Min Act: -0.1700
Data Index: 1872956 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.4046. Min Act: -0.1700
Data Index: 845081 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.3734. Min Act: -0.1700
Data Index: 8828762 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.3734. Min Act: -0.1700
Data Index: 3859054 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2796. Min Act: -0.1700
Data Index: 3932325 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.3109. Min Act: -0.1700
Data Index: 3465625 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2796. Min Act: -0.1700
Data Index: 6068982 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2796. Min Act: -0.1700
Data Index: 2579677 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2484. Min Act: -0.1700
Data Index: 6622452 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2484. Min Act: -0.1700
Data Index: 4257823 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2171. Min Act: -0.1700
Data Index: 2124945 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.2171. Min Act: -0.1700
Data Index: 1498136 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.1859. Min Act: -0.1700
Data Index: 5381882 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.1546. Min Act: -0.1700
Data Index: 5242438 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.1546. Min Act: -0.1700
Data Index: 4590862 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.1234. Min Act: -0.1700
Data Index: 5354880 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19