Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 86 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.2976. Min Act: -0.1700
Data Index: 2512635 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0476. Min Act: -0.1700
Data Index: 4011879 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0476. Min Act: -0.1700
Data Index: 574613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0476. Min Act: -0.1700
Data Index: 4949993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0476. Min Act: -0.1700
Data Index: 3530683 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0163. Min Act: -0.1700
Data Index: 1515787 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9851. Min Act: -0.1700
Data Index: 4835492 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9851. Min Act: -0.1699
Data Index: 2282926 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0163. Min Act: -0.1700
Data Index: 7529313 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2976. Min Range: -5.2976
Max Act: 5.0163. Min Act: -0.1700
Data Index: 3746974 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3421671 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2303066 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9226. Min Act: -0.1700
Data Index: 357717 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9226. Min Act: -0.1700
Data Index: 3781990 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2254665 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.8913. Min Act: -0.1700
Data Index: 7119154 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.8913. Min Act: -0.1700
Data Index: 3992876 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.8913. Min Act: -0.1700
Data Index: 7120527 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.8913. Min Act: -0.1700
Data Index: 6661263 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2976. Min Range: -5.2976
Max Act: 4.8601. Min Act: -0.1700
Data Index: 5907101 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19