Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4849 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1349. Min Range: -8.1349
Max Act: 8.1349. Min Act: -0.1700
Data Index: 540439 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.8849. Min Act: -0.1700
Data Index: 1999691 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.7599. Min Act: -0.1700
Data Index: 3709553 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.5411. Min Act: -0.1700
Data Index: 8743893 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.3224. Min Act: -0.1700
Data Index: 8611620 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.2911. Min Act: -0.1700
Data Index: 1484875 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.2599. Min Act: -0.1700
Data Index: 1971563 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.2599. Min Act: -0.1700
Data Index: 6828790 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.2911. Min Act: -0.1700
Data Index: 7412038 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1974. Min Act: -0.1700
Data Index: 8752629 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1661. Min Act: -0.1700
Data Index: 4242801 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1349. Min Act: -0.1700
Data Index: 1637210 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1661. Min Act: -0.1700
Data Index: 4552612 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1036. Min Act: -0.1700
Data Index: 6670237 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1349. Min Act: -0.1700
Data Index: 5260342 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1349. Min Act: -0.1700
Data Index: 3512092 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.1036. Min Act: -0.1700
Data Index: 6255031 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.0724. Min Act: -0.1700
Data Index: 3396097 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.0724. Min Act: -0.1700
Data Index: 8450215 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1349. Min Range: -8.1349
Max Act: 7.0099. Min Act: -0.1700
Data Index: 3086735 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19