Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.6642. Min Act: -0.1700
Data Index: 3694178 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.6016. Min Act: -0.1700
Data Index: 4988354 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.6016. Min Act: -0.1700
Data Index: 2339275 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.6016. Min Act: -0.1700
Data Index: 3571873 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 1177263 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5703. Min Act: -0.1700
Data Index: 5407278 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 2552295 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 2759446 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 6493397 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 6123726 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 6201691 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5390. Min Act: -0.1700
Data Index: 2260593 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.5077. Min Act: -0.1700
Data Index: 3479725 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4450. Min Act: -0.1700
Data Index: 4510484 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4450. Min Act: -0.1700
Data Index: 2537160 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4763. Min Act: -0.1700
Data Index: 4092782 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4763. Min Act: -0.1700
Data Index: 1004979 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4763. Min Act: -0.1700
Data Index: 8761288 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4763. Min Act: -0.1700
Data Index: 6301292 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6642. Min Range: -3.6642
Max Act: 3.4450. Min Act: -0.1700
Data Index: 5867594 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19