Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5350 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.6852. Min Act: -0.1700
Data Index: 631184 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.5602. Min Act: -0.1700
Data Index: 3338222 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.5290. Min Act: -0.1700
Data Index: 22001 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.5602. Min Act: -0.1700
Data Index: 405852 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.5290. Min Act: -0.1700
Data Index: 4757896 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4977. Min Act: -0.1700
Data Index: 5541396 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4977. Min Act: -0.1700
Data Index: 7909474 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 6695326 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 5663 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 5076549 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 4333496 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 2609594 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 509908 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 5272804 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 7501677 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4352. Min Act: -0.1700
Data Index: 1638346 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4352. Min Act: -0.1700
Data Index: 7036264 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4040. Min Act: -0.1700
Data Index: 6094794 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4352. Min Act: -0.1700
Data Index: 5101113 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4040. Min Act: -0.1700
Data Index: 8253758 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19