Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0725. Min Range: -5.0725
Max Act: 5.0725. Min Act: -0.1700
Data Index: 8162621 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0725. Min Range: -5.0725
Max Act: 5.0412. Min Act: -0.1700
Data Index: 5993508 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0725. Min Range: -5.0725
Max Act: 5.0100. Min Act: -0.1700
Data Index: 3717311 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.9787. Min Act: -0.1700
Data Index: 389845 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.9787. Min Act: -0.1700
Data Index: 6124383 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.9787. Min Act: -0.1700
Data Index: 5546741 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.9475. Min Act: -0.1700
Data Index: 6765682 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.9162. Min Act: -0.1700
Data Index: 5753079 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8537. Min Act: -0.1700
Data Index: 6296133 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8537. Min Act: -0.1700
Data Index: 2851592 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8225. Min Act: -0.1700
Data Index: 1381072 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8537. Min Act: -0.1700
Data Index: 3471424 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8225. Min Act: -0.1700
Data Index: 5344174 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8537. Min Act: -0.1700
Data Index: 1122015 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.7912. Min Act: -0.1700
Data Index: 1953764 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8225. Min Act: -0.1700
Data Index: 2752420 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.7912. Min Act: -0.1700
Data Index: 6770045 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.7912. Min Act: -0.1700
Data Index: 4379725 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.8225. Min Act: -0.1700
Data Index: 3489941 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0725. Min Range: -5.0725
Max Act: 4.7600. Min Act: -0.1700
Data Index: 1001190 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19