Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.9172. Min Act: -0.1700
Data Index: 4259072 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.6047. Min Act: -0.1700
Data Index: 4327957 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.6359. Min Act: -0.1700
Data Index: 4389689 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.5422. Min Act: -0.1700
Data Index: 2311601 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.5734. Min Act: -0.1700
Data Index: 6233435 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.5422. Min Act: -0.1700
Data Index: 7386454 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.5109. Min Act: -0.1700
Data Index: 8134847 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.5422. Min Act: -0.1700
Data Index: 4216131 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4797. Min Act: -0.1700
Data Index: 7922489 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4797. Min Act: -0.1700
Data Index: 4598762 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4797. Min Act: -0.1700
Data Index: 4561492 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4797. Min Act: -0.1700
Data Index: 7227223 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4797. Min Act: -0.1700
Data Index: 8167621 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4797. Min Act: -0.1700
Data Index: 2117899 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4484. Min Act: -0.1700
Data Index: 8507920 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4484. Min Act: -0.1700
Data Index: 5963757 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4484. Min Act: -0.1700
Data Index: 2607852 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4172. Min Act: -0.1700
Data Index: 7124384 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.4484. Min Act: -0.1700
Data Index: 4869893 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9172. Min Range: -4.9172
Max Act: 4.3859. Min Act: -0.1700
Data Index: 2014134 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19