Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1000 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.2423. Min Act: -0.1700
Data Index: 3949212 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.1173. Min Act: -0.1700
Data Index: 5524806 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.0861. Min Act: -0.1700
Data Index: 1992182 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.0861. Min Act: -0.1700
Data Index: 3465225 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.0861. Min Act: -0.1700
Data Index: 3464364 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.0548. Min Act: -0.1700
Data Index: 4436524 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.0236. Min Act: -0.1700
Data Index: 4032213 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2423. Min Range: -5.2423
Max Act: 5.0236. Min Act: -0.1700
Data Index: 4703865 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9923. Min Act: -0.1700
Data Index: 6754436 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9611. Min Act: -0.1700
Data Index: 2950767 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9611. Min Act: -0.1700
Data Index: 1215657 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9923. Min Act: -0.1700
Data Index: 5737323 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9298. Min Act: -0.1700
Data Index: 2454831 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9298. Min Act: -0.1700
Data Index: 5619951 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9611. Min Act: -0.1700
Data Index: 5139763 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9298. Min Act: -0.1700
Data Index: 8565714 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.9298. Min Act: -0.1700
Data Index: 3696365 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.8986. Min Act: -0.1700
Data Index: 653373 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.8986. Min Act: -0.1700
Data Index: 4027301 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2423. Min Range: -5.2423
Max Act: 4.8986. Min Act: -0.1700
Data Index: 428088 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19