Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6333 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.3890. Min Act: -0.1700
Data Index: 848541 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.3265. Min Act: -0.1700
Data Index: 8168950 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.3265. Min Act: -0.1700
Data Index: 5631887 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.2640. Min Act: -0.1700
Data Index: 1947043 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.2015. Min Act: -0.1700
Data Index: 6473794 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.2015. Min Act: -0.1700
Data Index: 8049760 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.2015. Min Act: -0.1700
Data Index: 3409782 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.2015. Min Act: -0.1700
Data Index: 6800719 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.2015. Min Act: -0.1700
Data Index: 2232227 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.0765. Min Act: -0.1700
Data Index: 3662638 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3890. Min Range: -8.3890
Max Act: 8.0453. Min Act: -0.1700
Data Index: 7354267 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.8265. Min Act: -0.1700
Data Index: 8199082 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.7953. Min Act: -0.1700
Data Index: 1979534 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.7953. Min Act: -0.1700
Data Index: 4944098 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.7328. Min Act: -0.1700
Data Index: 455602 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.7015. Min Act: -0.1700
Data Index: 6541784 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.7015. Min Act: -0.1700
Data Index: 6303111 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.6703. Min Act: -0.1700
Data Index: 7545611 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.6703. Min Act: -0.1700
Data Index: 1826098 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3890. Min Range: -8.3890
Max Act: 7.6703. Min Act: -0.1700
Data Index: 4787576 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19