Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0418. Min Range: -5.0418
Max Act: 5.0418. Min Act: -0.1700
Data Index: 3050229 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0418. Min Range: -5.0418
Max Act: 5.0106. Min Act: -0.1700
Data Index: 1697068 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.9793. Min Act: -0.1700
Data Index: 7671423 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.9481. Min Act: -0.1700
Data Index: 5209909 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.9481. Min Act: -0.1700
Data Index: 7877605 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.9481. Min Act: -0.1700
Data Index: 4130744 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.9481. Min Act: -0.1700
Data Index: 6130819 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.9481. Min Act: -0.1700
Data Index: 1370800 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.8543. Min Act: -0.1700
Data Index: 3652711 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.8543. Min Act: -0.1700
Data Index: 5406637 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.8231. Min Act: -0.1700
Data Index: 2466793 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.8231. Min Act: -0.1700
Data Index: 3043180 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.8231. Min Act: -0.1700
Data Index: 1155128 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7918. Min Act: -0.1700
Data Index: 7204019 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7918. Min Act: -0.1700
Data Index: 5921613 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7918. Min Act: -0.1700
Data Index: 1394044 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7918. Min Act: -0.1700
Data Index: 1183353 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7606. Min Act: -0.1700
Data Index: 7734836 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7918. Min Act: -0.1700
Data Index: 2301867 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0418. Min Range: -5.0418
Max Act: 4.7606. Min Act: -0.1700
Data Index: 642188 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19