Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 629 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.4832. Min Act: -0.1700
Data Index: 4555436 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.4207. Min Act: -0.1700
Data Index: 3422541 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.2020. Min Act: -0.1700
Data Index: 2476380 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.1082. Min Act: -0.1700
Data Index: 7424859 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.0770. Min Act: -0.1700
Data Index: 7225902 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.0145. Min Act: -0.1700
Data Index: 1167779 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.0457. Min Act: -0.1700
Data Index: 6218977 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4832. Min Range: -6.4832
Max Act: 6.0145. Min Act: -0.1700
Data Index: 3696726 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.9520. Min Act: -0.1700
Data Index: 5345018 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.9520. Min Act: -0.1700
Data Index: 4405569 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.9520. Min Act: -0.1700
Data Index: 8241735 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8895. Min Act: -0.1700
Data Index: 5205171 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8895. Min Act: -0.1700
Data Index: 2868834 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8895. Min Act: -0.1700
Data Index: 1597611 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8895. Min Act: -0.1700
Data Index: 8760766 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8582. Min Act: -0.1700
Data Index: 4054128 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8582. Min Act: -0.1700
Data Index: 124998 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8270. Min Act: -0.1700
Data Index: 263198 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8895. Min Act: -0.1700
Data Index: 4161207 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4832. Min Range: -6.4832
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2420844 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19