Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.2785. Min Act: -0.1700
Data Index: 2426505 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.2785. Min Act: -0.1700
Data Index: 3401597 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.1848. Min Act: -0.1700
Data Index: 629489 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.1848. Min Act: -0.1700
Data Index: 7073731 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0910. Min Act: -0.1700
Data Index: 8483125 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0910. Min Act: -0.1700
Data Index: 374389 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0598. Min Act: -0.1700
Data Index: 6397030 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0598. Min Act: -0.1700
Data Index: 3437753 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0598. Min Act: -0.1700
Data Index: 6857922 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0285. Min Act: -0.1700
Data Index: 7431585 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0285. Min Act: -0.1700
Data Index: 3317652 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2785. Min Range: -5.2785
Max Act: 5.0285. Min Act: -0.1700
Data Index: 8699868 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9973. Min Act: -0.1700
Data Index: 1438298 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9973. Min Act: -0.1700
Data Index: 4811707 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9973. Min Act: -0.1700
Data Index: 2902162 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9973. Min Act: -0.1700
Data Index: 4676079 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9973. Min Act: -0.1700
Data Index: 3894863 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9973. Min Act: -0.1700
Data Index: 5351375 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9660. Min Act: -0.1700
Data Index: 4136421 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2785. Min Range: -5.2785
Max Act: 4.9660. Min Act: -0.1700
Data Index: 5111587 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19