Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.3282. Min Act: -0.1700
Data Index: 1176318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.2657. Min Act: -0.1700
Data Index: 6368293 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 1204228 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.2032. Min Act: -0.1700
Data Index: 2702689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 887953 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 954267 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 1846842 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 5891452 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1699
Data Index: 1494917 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 1547338 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 6839718 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 6766969 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1699
Data Index: 766547 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 140379 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 5762147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 1342400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 958495 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 334516 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 5425747 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 4929362 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19