Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.7701. Min Act: -0.1700
Data Index: 7249266 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.7388. Min Act: -0.1700
Data Index: 5593078 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.6763. Min Act: -0.1700
Data Index: 5576017 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.6763. Min Act: -0.1700
Data Index: 7693478 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.7076. Min Act: -0.1700
Data Index: 388129 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.6138. Min Act: -0.1700
Data Index: 2002680 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5826. Min Act: -0.1700
Data Index: 4783474 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.6138. Min Act: -0.1700
Data Index: 3142208 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.6138. Min Act: -0.1700
Data Index: 7857589 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.6138. Min Act: -0.1700
Data Index: 6313575 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5513. Min Act: -0.1700
Data Index: 7846342 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.4888. Min Act: -0.1700
Data Index: 7064081 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 7043677 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 5826332 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 6150356 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 3901734 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 1894958 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 3507326 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 6587267 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7701. Min Range: -5.7701
Max Act: 5.5201. Min Act: -0.1700
Data Index: 4901069 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19