Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 860 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2146. Min Range: -5.2146
Max Act: 5.2146. Min Act: -0.1700
Data Index: 6389020 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.9021. Min Act: -0.1700
Data Index: 8280448 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8708. Min Act: -0.1700
Data Index: 1674907 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8396. Min Act: -0.1700
Data Index: 7484254 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8396. Min Act: -0.1700
Data Index: 6056624 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8396. Min Act: -0.1700
Data Index: 6469686 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8083. Min Act: -0.1700
Data Index: 5131494 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8396. Min Act: -0.1700
Data Index: 4146960 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.7771. Min Act: -0.1700
Data Index: 6731827 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.8083. Min Act: -0.1700
Data Index: 7442338 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.7771. Min Act: -0.1700
Data Index: 6019879 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.7458. Min Act: -0.1700
Data Index: 5599393 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.7458. Min Act: -0.1700
Data Index: 6991059 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.7146. Min Act: -0.1700
Data Index: 1098993 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.7146. Min Act: -0.1700
Data Index: 617503 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.6833. Min Act: -0.1700
Data Index: 8342892 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.6521. Min Act: -0.1700
Data Index: 1892992 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.6521. Min Act: -0.1700
Data Index: 390527 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.6833. Min Act: -0.1700
Data Index: 3133601 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2146. Min Range: -5.2146
Max Act: 4.6521. Min Act: -0.1700
Data Index: 2435841 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19