Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.4184. Min Act: -0.1700
Data Index: 7228739 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.4496. Min Act: -0.1700
Data Index: 1369996 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.4184. Min Act: -0.1700
Data Index: 2864639 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.4184. Min Act: -0.1700
Data Index: 4452561 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.3871. Min Act: -0.1700
Data Index: 613504 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.3246. Min Act: -0.1700
Data Index: 7969963 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2933. Min Act: -0.1700
Data Index: 5113926 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.3246. Min Act: -0.1700
Data Index: 3017765 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2621. Min Act: -0.1700
Data Index: 4353480 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2308. Min Act: -0.1700
Data Index: 8452660 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2308. Min Act: -0.1700
Data Index: 4049827 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7951891 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2308. Min Act: -0.1700
Data Index: 890838 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2308. Min Act: -0.1700
Data Index: 27696 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.1996. Min Act: -0.1700
Data Index: 3939838 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2621. Min Act: -0.1700
Data Index: 4136405 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2308. Min Act: -0.1700
Data Index: 7424752 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.2308. Min Act: -0.1700
Data Index: 1227831 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.1683. Min Act: -0.1700
Data Index: 3736830 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4496. Min Range: -4.4496
Max Act: 4.1996. Min Act: -0.1700
Data Index: 1612766 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19