Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4438 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0937. Min Range: -6.0937
Max Act: 6.0937. Min Act: -0.1700
Data Index: 3345767 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0937. Min Range: -6.0937
Max Act: 6.0312. Min Act: -0.1700
Data Index: 5244902 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.9687. Min Act: -0.1700
Data Index: 105670 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.9374. Min Act: -0.1700
Data Index: 3588291 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.9062. Min Act: -0.1700
Data Index: 2241017 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.9062. Min Act: -0.1700
Data Index: 6174428 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.8749. Min Act: -0.1700
Data Index: 85069 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.8437. Min Act: -0.1700
Data Index: 2923127 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.8124. Min Act: -0.1700
Data Index: 3784387 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.8437. Min Act: -0.1700
Data Index: 7934802 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.8124. Min Act: -0.1700
Data Index: 8821388 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.8437. Min Act: -0.1700
Data Index: 5733342 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.7812. Min Act: -0.1700
Data Index: 5365118 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.7187. Min Act: -0.1700
Data Index: 6838607 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.7499. Min Act: -0.1700
Data Index: 7284493 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.7187. Min Act: -0.1700
Data Index: 7795647 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.7187. Min Act: -0.1700
Data Index: 7751794 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.7187. Min Act: -0.1700
Data Index: 5288336 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.6874. Min Act: -0.1700
Data Index: 2519603 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0937. Min Range: -6.0937
Max Act: 5.6874. Min Act: -0.1700
Data Index: 2840840 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19