Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3657. Min Range: -5.3657
Max Act: 5.3657. Min Act: -0.1700
Data Index: 4150841 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3657. Min Range: -5.3657
Max Act: 5.0220. Min Act: -0.1700
Data Index: 3469116 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.9907. Min Act: -0.1700
Data Index: 5068785 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.8970. Min Act: -0.1700
Data Index: 7060659 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.9282. Min Act: -0.1700
Data Index: 3553527 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.8970. Min Act: -0.1700
Data Index: 7328224 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.8657. Min Act: -0.1700
Data Index: 6508556 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.8345. Min Act: -0.1700
Data Index: 7659412 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.7720. Min Act: -0.1700
Data Index: 7241581 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.7720. Min Act: -0.1700
Data Index: 8006809 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.7720. Min Act: -0.1700
Data Index: 2139154 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.7720. Min Act: -0.1700
Data Index: 1725720 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 177432 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6782. Min Act: -0.1700
Data Index: 6722415 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6782. Min Act: -0.1700
Data Index: 2642209 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6782. Min Act: -0.1700
Data Index: 4348189 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6470. Min Act: -0.1700
Data Index: 3915313 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6782. Min Act: -0.1700
Data Index: 3705679 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6782. Min Act: -0.1700
Data Index: 167164 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3657. Min Range: -5.3657
Max Act: 4.6782. Min Act: -0.1700
Data Index: 5348011 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19