Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.7808. Min Act: -0.1700
Data Index: 692311 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.7496. Min Act: -0.1700
Data Index: 5235271 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.6871. Min Act: -0.1700
Data Index: 1049372 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.5621. Min Act: -0.1700
Data Index: 6952180 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.5933. Min Act: -0.1700
Data Index: 6411147 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.5933. Min Act: -0.1700
Data Index: 1486589 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.5621. Min Act: -0.1700
Data Index: 2324502 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.5621. Min Act: -0.1700
Data Index: 533178 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4996. Min Act: -0.1700
Data Index: 8778536 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.5308. Min Act: -0.1700
Data Index: 3499566 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4683. Min Act: -0.1700
Data Index: 198997 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4683. Min Act: -0.1700
Data Index: 1359631 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4683. Min Act: -0.1700
Data Index: 5647897 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4683. Min Act: -0.1700
Data Index: 5424773 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4371. Min Act: -0.1700
Data Index: 5401727 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4058. Min Act: -0.1700
Data Index: 151825 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4058. Min Act: -0.1700
Data Index: 2575386 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4058. Min Act: -0.1700
Data Index: 312454 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4058. Min Act: -0.1700
Data Index: 4144910 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7808. Min Range: -6.7808
Max Act: 6.4371. Min Act: -0.1700
Data Index: 962553 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19