Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.4547. Min Act: -0.1700
Data Index: 8619880 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.2360. Min Act: -0.1700
Data Index: 8193400 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.2047. Min Act: -0.1700
Data Index: 543455 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.1735. Min Act: -0.1700
Data Index: 7321614 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.1735. Min Act: -0.1700
Data Index: 4797540 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.1422. Min Act: -0.1700
Data Index: 8611730 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.1422. Min Act: -0.1700
Data Index: 2674329 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.1422. Min Act: -0.1700
Data Index: 7728860 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.1422. Min Act: -0.1700
Data Index: 575210 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.0797. Min Act: -0.1700
Data Index: 6223661 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.0485. Min Act: -0.1700
Data Index: 4334485 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.0172. Min Act: -0.1700
Data Index: 5860631 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.0172. Min Act: -0.1700
Data Index: 4706469 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.0485. Min Act: -0.1700
Data Index: 2764549 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4547. Min Range: -6.4547
Max Act: 5.9860. Min Act: -0.1700
Data Index: 639354 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4547. Min Range: -6.4547
Max Act: 5.9860. Min Act: -0.1700
Data Index: 3455878 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4547. Min Range: -6.4547
Max Act: 5.9860. Min Act: -0.1700
Data Index: 7118330 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4547. Min Range: -6.4547
Max Act: 6.0172. Min Act: -0.1700
Data Index: 383707 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4547. Min Range: -6.4547
Max Act: 5.9547. Min Act: -0.1700
Data Index: 6081939 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4547. Min Range: -6.4547
Max Act: 5.9860. Min Act: -0.1700
Data Index: 1752687 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19