Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4998 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0476. Min Range: -5.0476
Max Act: 5.0476. Min Act: -0.1700
Data Index: 5753333 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7038. Min Act: -0.1700
Data Index: 8827012 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.5788. Min Act: -0.1700
Data Index: 71556 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4850. Min Act: -0.1700
Data Index: 590647 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4538. Min Act: -0.1700
Data Index: 7777587 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4538. Min Act: -0.1700
Data Index: 6486316 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8737811 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4225. Min Act: -0.1700
Data Index: 2068965 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4225. Min Act: -0.1700
Data Index: 737538 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4538. Min Act: -0.1700
Data Index: 6762722 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4225. Min Act: -0.1700
Data Index: 4082495 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4225. Min Act: -0.1700
Data Index: 7610387 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4225. Min Act: -0.1700
Data Index: 252015 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.3913. Min Act: -0.1700
Data Index: 3796999 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.4225. Min Act: -0.1700
Data Index: 7053026 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.3600. Min Act: -0.1700
Data Index: 7542874 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.3600. Min Act: -0.1700
Data Index: 7142248 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.3600. Min Act: -0.1700
Data Index: 7968886 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1208167 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.3600. Min Act: -0.1700
Data Index: 298551 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19