Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4427 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.7323. Min Act: -0.1700
Data Index: 6035796 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.6697. Min Act: -0.1700
Data Index: 3234355 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.6228. Min Act: -0.1700
Data Index: 4068233 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.5915. Min Act: -0.1700
Data Index: 4511269 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.5289. Min Act: -0.1700
Data Index: 3225196 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.5132. Min Act: -0.1700
Data Index: 7381663 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4975. Min Act: -0.1700
Data Index: 5254933 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4662. Min Act: -0.1700
Data Index: 1847801 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4662. Min Act: -0.1700
Data Index: 1459821 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4505. Min Act: -0.1700
Data Index: 1436574 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4349. Min Act: -0.1700
Data Index: 2526386 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4349. Min Act: -0.1700
Data Index: 204112 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4349. Min Act: -0.1700
Data Index: 7052864 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4192. Min Act: -0.1700
Data Index: 166776 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4192. Min Act: -0.1700
Data Index: 8422726 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4035. Min Act: -0.1700
Data Index: 753245 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4035. Min Act: -0.1700
Data Index: 7338090 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.4035. Min Act: -0.1700
Data Index: 7202759 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.3722. Min Act: -0.1700
Data Index: 5285955 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7323. Min Range: -3.7323
Max Act: 3.3878. Min Act: -0.1700
Data Index: 602223 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19