Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4513 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.8408. Min Act: -0.1700
Data Index: 7444237 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.8408. Min Act: -0.1700
Data Index: 8596307 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.7783. Min Act: -0.1700
Data Index: 4206334 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.7470. Min Act: -0.1700
Data Index: 5124448 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.7470. Min Act: -0.1700
Data Index: 5127634 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6845. Min Act: -0.1700
Data Index: 33932 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6845. Min Act: -0.1700
Data Index: 3083357 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6845. Min Act: -0.1700
Data Index: 5044678 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 4574605 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 6678131 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6533. Min Act: -0.1700
Data Index: 3304340 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6533. Min Act: -0.1700
Data Index: 1393386 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6533. Min Act: -0.1700
Data Index: 1155237 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6533. Min Act: -0.1700
Data Index: 4825152 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 2395020 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 2031556 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 5136227 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.5908. Min Act: -0.1700
Data Index: 6329576 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 4571277 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8408. Min Range: -5.8408
Max Act: 5.6220. Min Act: -0.1700
Data Index: 3856290 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19