Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0575. Min Range: -7.0575
Max Act: 7.0575. Min Act: -0.1700
Data Index: 6183173 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.9950. Min Act: -0.1700
Data Index: 8107508 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.9325. Min Act: -0.1700
Data Index: 3688951 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.9012. Min Act: -0.1700
Data Index: 8623052 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.8700. Min Act: -0.1700
Data Index: 3152664 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.8700. Min Act: -0.1700
Data Index: 3500714 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.8075. Min Act: -0.1700
Data Index: 5772524 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.7762. Min Act: -0.1700
Data Index: 8611330 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.7762. Min Act: -0.1700
Data Index: 6999270 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.7450. Min Act: -0.1700
Data Index: 4647547 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6825. Min Act: -0.1700
Data Index: 2632801 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6825. Min Act: -0.1700
Data Index: 1523375 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6825. Min Act: -0.1700
Data Index: 104180 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6512. Min Act: -0.1700
Data Index: 6427245 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6825. Min Act: -0.1700
Data Index: 2239220 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6512. Min Act: -0.1700
Data Index: 4339612 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6512. Min Act: -0.1700
Data Index: 3935180 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6512. Min Act: -0.1700
Data Index: 8344653 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6825. Min Act: -0.1700
Data Index: 4094605 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0575. Min Range: -7.0575
Max Act: 6.6200. Min Act: -0.1700
Data Index: 7817968 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19