Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.8904. Min Act: -0.1700
Data Index: 5923182 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.8269. Min Act: -0.1700
Data Index: 3136708 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.7791. Min Act: -0.1700
Data Index: 7633473 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.7312. Min Act: -0.1700
Data Index: 6784829 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.7312. Min Act: -0.1700
Data Index: 7393791 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.7153. Min Act: -0.1700
Data Index: 1232447 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6672. Min Act: -0.1700
Data Index: 1797869 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6512. Min Act: -0.1700
Data Index: 7120476 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6672. Min Act: -0.1700
Data Index: 2362675 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6512. Min Act: -0.1700
Data Index: 129983 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6351. Min Act: -0.1700
Data Index: 8336568 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6512. Min Act: -0.1700
Data Index: 6164682 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6672. Min Act: -0.1700
Data Index: 7426011 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6030. Min Act: -0.1700
Data Index: 7330531 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6030. Min Act: -0.1700
Data Index: 7717703 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6351. Min Act: -0.1700
Data Index: 4180294 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.5869. Min Act: -0.1700
Data Index: 2109517 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.6030. Min Act: -0.1700
Data Index: 4015260 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.5869. Min Act: -0.1700
Data Index: 6343038 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8904. Min Range: -2.8904
Max Act: 2.5869. Min Act: -0.1700
Data Index: 6095512 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19