Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1405. Min Range: -8.1405
Max Act: 8.1405. Min Act: -0.1700
Data Index: 5743548 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.7655. Min Act: -0.1700
Data Index: 5344957 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.7030. Min Act: -0.1700
Data Index: 2218969 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.5780. Min Act: -0.1700
Data Index: 8618893 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.5155. Min Act: -0.1700
Data Index: 4025240 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.5155. Min Act: -0.1700
Data Index: 3581673 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.5155. Min Act: -0.1700
Data Index: 1004400 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.4530. Min Act: -0.1700
Data Index: 5096718 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.4530. Min Act: -0.1700
Data Index: 5767664 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.4218. Min Act: -0.1700
Data Index: 6731951 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.3593. Min Act: -0.1700
Data Index: 3746170 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.3280. Min Act: -0.1700
Data Index: 4997249 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.3280. Min Act: -0.1700
Data Index: 4705892 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2968. Min Act: -0.1700
Data Index: 905387 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2655. Min Act: -0.1700
Data Index: 8414404 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2343. Min Act: -0.1700
Data Index: 5387518 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2655. Min Act: -0.1700
Data Index: 7375166 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2343. Min Act: -0.1700
Data Index: 2154035 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2655. Min Act: -0.1700
Data Index: 5090838 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1405. Min Range: -8.1405
Max Act: 7.2343. Min Act: -0.1700
Data Index: 7690180 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19