Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1658 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2893860 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.4231. Min Act: -0.1700
Data Index: 6328211 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.3919. Min Act: -0.1700
Data Index: 1264795 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.3606. Min Act: -0.1700
Data Index: 8575178 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.3294. Min Act: -0.1700
Data Index: 1418599 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2981. Min Act: -0.1700
Data Index: 1601841 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2669. Min Act: -0.1700
Data Index: 4074225 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2044. Min Act: -0.1700
Data Index: 8723591 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2356. Min Act: -0.1700
Data Index: 3424297 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2044. Min Act: -0.1700
Data Index: 3205006 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2044. Min Act: -0.1700
Data Index: 1462033 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2356. Min Act: -0.1700
Data Index: 3006510 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1731. Min Act: -0.1700
Data Index: 3379692 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1731. Min Act: -0.1700
Data Index: 1442609 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.2044. Min Act: -0.1700
Data Index: 7118926 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1731. Min Act: -0.1700
Data Index: 1064712 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1106. Min Act: -0.1700
Data Index: 6099616 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1731. Min Act: -0.1700
Data Index: 6205795 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1419. Min Act: -0.1700
Data Index: 411067 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7356. Min Range: -5.7356
Max Act: 5.1731. Min Act: -0.1700
Data Index: 6550964 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19