Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.7787. Min Act: -0.1700
Data Index: 2430693 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.7474. Min Act: -0.1700
Data Index: 7315312 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.6849. Min Act: -0.1700
Data Index: 4240156 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.5912. Min Act: -0.1700
Data Index: 5459197 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.5287. Min Act: -0.1700
Data Index: 1147723 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4974. Min Act: -0.1700
Data Index: 8058283 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4974. Min Act: -0.1700
Data Index: 6089523 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2972161 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4662. Min Act: -0.1700
Data Index: 5264487 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4662. Min Act: -0.1700
Data Index: 7333291 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4349. Min Act: -0.1700
Data Index: 1799129 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4974. Min Act: -0.1700
Data Index: 1388371 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.4349. Min Act: -0.1700
Data Index: 652703 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3724. Min Act: -0.1700
Data Index: 5024966 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3412. Min Act: -0.1700
Data Index: 3712830 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3724. Min Act: -0.1700
Data Index: 1659646 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3099. Min Act: -0.1700
Data Index: 3295179 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3099. Min Act: -0.1700
Data Index: 5869891 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3099. Min Act: -0.1700
Data Index: 3325272 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7787. Min Range: -5.7787
Max Act: 5.3099. Min Act: -0.1700
Data Index: 52566 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19