Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.5771. Min Act: -0.1700
Data Index: 4430127 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.4209. Min Act: -0.1700
Data Index: 1123069 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.3584. Min Act: -0.1700
Data Index: 3720058 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.2646. Min Act: -0.1700
Data Index: 4611277 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.2646. Min Act: -0.1700
Data Index: 465376 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.2334. Min Act: -0.1700
Data Index: 6417757 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.2021. Min Act: -0.1700
Data Index: 4008669 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.1709. Min Act: -0.1700
Data Index: 566389 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.1396. Min Act: -0.1700
Data Index: 2921542 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.1084. Min Act: -0.1700
Data Index: 1676057 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0771. Min Act: -0.1700
Data Index: 3923881 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0771. Min Act: -0.1700
Data Index: 3817094 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0459. Min Act: -0.1700
Data Index: 5479371 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0146. Min Act: -0.1700
Data Index: 4984377 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0146. Min Act: -0.1700
Data Index: 3984977 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9521. Min Act: -0.1700
Data Index: 1606395 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9521. Min Act: -0.1700
Data Index: 5999686 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9521. Min Act: -0.1700
Data Index: 6440894 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9521. Min Act: -0.1700
Data Index: 3582439 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9521. Min Act: -0.1700
Data Index: 580233 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19