Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.9325. Min Act: -0.1700
Data Index: 3700759 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.6200. Min Act: -0.1700
Data Index: 4985420 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.4325. Min Act: -0.1700
Data Index: 7790449 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.2763. Min Act: -0.1700
Data Index: 8164779 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.2138. Min Act: -0.1700
Data Index: 3849899 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.2138. Min Act: -0.1700
Data Index: 5211516 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.1513. Min Act: -0.1700
Data Index: 4369880 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.1513. Min Act: -0.1700
Data Index: 7182942 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0888. Min Act: -0.1700
Data Index: 7819618 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0888. Min Act: -0.1700
Data Index: 2422731 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 4317604 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 6402675 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 2781960 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 8667481 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9325. Min Range: -6.9325
Max Act: 6.0263. Min Act: -0.1700
Data Index: 6480417 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9325. Min Range: -6.9325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 664115 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9325. Min Range: -6.9325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 2755521 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9325. Min Range: -6.9325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 8452805 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9325. Min Range: -6.9325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 2869475 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9325. Min Range: -6.9325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 3406899 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19