Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.8354. Min Act: -0.1700
Data Index: 6896835 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.7104. Min Act: -0.1700
Data Index: 4611709 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.6479. Min Act: -0.1700
Data Index: 3139034 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.6479. Min Act: -0.1700
Data Index: 6461725 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.6167. Min Act: -0.1700
Data Index: 5894542 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.5542. Min Act: -0.1700
Data Index: 5489058 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.5854. Min Act: -0.1700
Data Index: 3788888 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.5542. Min Act: -0.1700
Data Index: 5384042 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.4917. Min Act: -0.1700
Data Index: 1157434 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.4917. Min Act: -0.1700
Data Index: 3355183 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.4917. Min Act: -0.1700
Data Index: 6019550 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.4604. Min Act: -0.1700
Data Index: 8119710 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.4292. Min Act: -0.1700
Data Index: 479521 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3979. Min Act: -0.1700
Data Index: 297563 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3666. Min Act: -0.1700
Data Index: 5022331 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3666. Min Act: -0.1700
Data Index: 8192589 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3666. Min Act: -0.1700
Data Index: 49113 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3666. Min Act: -0.1700
Data Index: 4696175 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3666. Min Act: -0.1700
Data Index: 8720699 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8354. Min Range: -4.8354
Max Act: 4.3666. Min Act: -0.1700
Data Index: 7043893 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19