Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4276 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.7290. Min Act: -0.1700
Data Index: 5629870 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6665. Min Act: -0.1700
Data Index: 5140785 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6665. Min Act: -0.1700
Data Index: 5629887 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 31347 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6040. Min Act: -0.1698
Data Index: 1883475 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 796275 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 7466552 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1697
Data Index: 7167499 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1699
Data Index: 7167498 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 2716861 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 3117925 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 6426361 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 1326096 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 1540125 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1699
Data Index: 4198178 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 6954393 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 3159346 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 1282225 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 2028120 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5102. Min Act: -0.1700
Data Index: 316800 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19