Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3378. Min Range: -7.3378
Max Act: 7.3378. Min Act: -0.1700
Data Index: 4336802 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3378. Min Range: -7.3378
Max Act: 7.1816. Min Act: -0.1700
Data Index: 390950 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3378. Min Range: -7.3378
Max Act: 7.1191. Min Act: -0.1700
Data Index: 8653747 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3378. Min Range: -7.3378
Max Act: 7.0566. Min Act: -0.1700
Data Index: 4081630 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.9003. Min Act: -0.1700
Data Index: 286484 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.9003. Min Act: -0.1700
Data Index: 933914 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.8691. Min Act: -0.1700
Data Index: 1261294 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.8378. Min Act: -0.1700
Data Index: 3074362 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.8378. Min Act: -0.1700
Data Index: 5507909 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.8378. Min Act: -0.1700
Data Index: 4808614 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.8066. Min Act: -0.1700
Data Index: 683915 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.8066. Min Act: -0.1700
Data Index: 1115116 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.7753. Min Act: -0.1700
Data Index: 1687676 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.7753. Min Act: -0.1700
Data Index: 3853927 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.7441. Min Act: -0.1700
Data Index: 5434305 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.7128. Min Act: -0.1700
Data Index: 4438910 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.6816. Min Act: -0.1700
Data Index: 2760192 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.6816. Min Act: -0.1700
Data Index: 4772163 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.6816. Min Act: -0.1700
Data Index: 782199 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3378. Min Range: -7.3378
Max Act: 6.6503. Min Act: -0.1700
Data Index: 712557 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19