Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5787. Min Range: -8.5787
Max Act: 8.5787. Min Act: -0.1700
Data Index: 6845317 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5787. Min Range: -8.5787
Max Act: 8.2349. Min Act: -0.1700
Data Index: 1449928 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5787. Min Range: -8.5787
Max Act: 8.1724. Min Act: -0.1700
Data Index: 1877645 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5787. Min Range: -8.5787
Max Act: 8.0162. Min Act: -0.1700
Data Index: 2502380 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.9849. Min Act: -0.1700
Data Index: 414262 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.7349. Min Act: -0.1700
Data Index: 8350812 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.7037. Min Act: -0.1700
Data Index: 8260719 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.6412. Min Act: -0.1700
Data Index: 928937 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.6099. Min Act: -0.1700
Data Index: 6590962 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.4537. Min Act: -0.1700
Data Index: 6282084 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.3912. Min Act: -0.1700
Data Index: 2404790 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.3912. Min Act: -0.1700
Data Index: 8437258 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.3599. Min Act: -0.1700
Data Index: 3031403 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.3287. Min Act: -0.1700
Data Index: 637576 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.2974. Min Act: -0.1700
Data Index: 6237721 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.2662. Min Act: -0.1700
Data Index: 4862044 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.2662. Min Act: -0.1700
Data Index: 6445436 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.2662. Min Act: -0.1700
Data Index: 1234860 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.2349. Min Act: -0.1700
Data Index: 4468598 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5787. Min Range: -8.5787
Max Act: 7.2349. Min Act: -0.1700
Data Index: 4681026 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19