Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5837 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.8657. Min Act: -0.1700
Data Index: 1160591 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.8657. Min Act: -0.1700
Data Index: 4480467 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.8032. Min Act: -0.1700
Data Index: 8831176 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.8345. Min Act: -0.1700
Data Index: 6468194 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7720. Min Act: -0.1700
Data Index: 4480464 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.8032. Min Act: -0.1700
Data Index: 5707720 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7720. Min Act: -0.1700
Data Index: 2569292 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 6499479 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 6778919 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 5970536 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 4480463 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 4949168 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 4683610 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 7960260 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 7245093 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7407. Min Act: -0.1700
Data Index: 1373938 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7095. Min Act: -0.1700
Data Index: 6250538 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7095. Min Act: -0.1700
Data Index: 3955793 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7095. Min Act: -0.1700
Data Index: 2817875 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8657. Min Range: -4.8657
Max Act: 4.7095. Min Act: -0.1700
Data Index: 840360 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19