Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.6831. Min Act: -0.1700
Data Index: 7088168 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.7300. Min Act: -0.1700
Data Index: 8042055 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.7300. Min Act: -0.1700
Data Index: 7400808 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.6674. Min Act: -0.1700
Data Index: 4330832 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.6831. Min Act: -0.1700
Data Index: 1399737 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.6518. Min Act: -0.1700
Data Index: 3282303 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.6205. Min Act: -0.1700
Data Index: 8580096 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.5579. Min Act: -0.1700
Data Index: 1399739 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.5579. Min Act: -0.1700
Data Index: 5550085 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.5579. Min Act: -0.1700
Data Index: 5886033 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4796. Min Act: -0.1700
Data Index: 310319 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.5109. Min Act: -0.1700
Data Index: 5248191 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.5266. Min Act: -0.1700
Data Index: 7851325 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4953. Min Act: -0.1700
Data Index: 1399746 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4953. Min Act: -0.1700
Data Index: 3725822 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4326. Min Act: -0.1700
Data Index: 1787136 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4483. Min Act: -0.1700
Data Index: 3654287 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4169. Min Act: -0.1700
Data Index: 5248194 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.4169. Min Act: -0.1700
Data Index: 6832604 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7300. Min Range: -3.7300
Max Act: 3.3542. Min Act: -0.1700
Data Index: 7011500 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19