Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0033. Min Range: -3.0033
Max Act: 3.0033. Min Act: -0.1700
Data Index: 6324289 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.9083. Min Act: -0.1700
Data Index: 4410970 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.9083. Min Act: -0.1700
Data Index: 8078515 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.8448. Min Act: -0.1700
Data Index: 5463622 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.8130. Min Act: -0.1700
Data Index: 3431010 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7812. Min Act: -0.1700
Data Index: 2263694 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7652. Min Act: -0.1700
Data Index: 7505772 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7652. Min Act: -0.1700
Data Index: 3716988 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7652. Min Act: -0.1700
Data Index: 4957788 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7493. Min Act: -0.1700
Data Index: 5779636 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7493. Min Act: -0.1700
Data Index: 1066386 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7173. Min Act: -0.1700
Data Index: 213554 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7173. Min Act: -0.1700
Data Index: 2090621 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7173. Min Act: -0.1700
Data Index: 8206045 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7173. Min Act: -0.1700
Data Index: 1637317 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7013. Min Act: -0.1700
Data Index: 1558154 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7013. Min Act: -0.1700
Data Index: 837079 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7013. Min Act: -0.1700
Data Index: 1407231 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7013. Min Act: -0.1700
Data Index: 6568687 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0033. Min Range: -3.0033
Max Act: 2.7013. Min Act: -0.1700
Data Index: 4106850 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19