Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 986 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0798. Min Range: -5.0798
Max Act: 5.0798. Min Act: -0.1700
Data Index: 2073564 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.9548. Min Act: -0.1700
Data Index: 2925914 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.8298. Min Act: -0.1700
Data Index: 7277033 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7673. Min Act: -0.1700
Data Index: 2557023 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7673. Min Act: -0.1700
Data Index: 7638019 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7985. Min Act: -0.1700
Data Index: 7092158 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7673. Min Act: -0.1700
Data Index: 6395741 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7360. Min Act: -0.1700
Data Index: 8455344 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7673. Min Act: -0.1700
Data Index: 5528597 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7360. Min Act: -0.1700
Data Index: 2073178 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7360. Min Act: -0.1700
Data Index: 6455325 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7048. Min Act: -0.1700
Data Index: 4159276 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7048. Min Act: -0.1700
Data Index: 1131350 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7048. Min Act: -0.1700
Data Index: 719837 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.6735. Min Act: -0.1700
Data Index: 327047 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7048. Min Act: -0.1700
Data Index: 2557149 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.7048. Min Act: -0.1700
Data Index: 4974000 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.6735. Min Act: -0.1700
Data Index: 5725858 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.6735. Min Act: -0.1700
Data Index: 831705 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0798. Min Range: -5.0798
Max Act: 4.6735. Min Act: -0.1700
Data Index: 6118492 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19