Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1662 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.6832. Min Act: -0.1700
Data Index: 1697108 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.6206. Min Act: -0.1700
Data Index: 4691308 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.5110. Min Act: -0.1700
Data Index: 610102 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.5267. Min Act: -0.1700
Data Index: 376848 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4954. Min Act: -0.1700
Data Index: 7144655 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.5267. Min Act: -0.1700
Data Index: 5772126 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.5110. Min Act: -0.1700
Data Index: 7113019 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4640. Min Act: -0.1700
Data Index: 7395215 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4484. Min Act: -0.1700
Data Index: 2802646 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4484. Min Act: -0.1700
Data Index: 757603 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4327. Min Act: -0.1700
Data Index: 6934471 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4327. Min Act: -0.1700
Data Index: 7985615 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4327. Min Act: -0.1700
Data Index: 6417175 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4327. Min Act: -0.1700
Data Index: 7550697 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4170. Min Act: -0.1700
Data Index: 1655182 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4170. Min Act: -0.1700
Data Index: 5547173 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4170. Min Act: -0.1700
Data Index: 577982 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4013. Min Act: -0.1700
Data Index: 6430178 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.3857. Min Act: -0.1700
Data Index: 3847076 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6832. Min Range: -3.6832
Max Act: 3.4013. Min Act: -0.1700
Data Index: 7242037 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19