Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0381. Min Range: -5.0381
Max Act: 5.0381. Min Act: -0.1700
Data Index: 4825255 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.9756. Min Act: -0.1700
Data Index: 8561629 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.9443. Min Act: -0.1700
Data Index: 6107750 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.8506. Min Act: -0.1700
Data Index: 8790408 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.8506. Min Act: -0.1700
Data Index: 4841205 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.8193. Min Act: -0.1700
Data Index: 8695251 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7881. Min Act: -0.1700
Data Index: 2437630 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 3013642 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7881. Min Act: -0.1700
Data Index: 3419624 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7568. Min Act: -0.1700
Data Index: 2773304 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 7160827 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 6769228 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 3194236 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.6943. Min Act: -0.1700
Data Index: 2518329 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 1306486 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 4093041 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.6943. Min Act: -0.1700
Data Index: 8236752 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7568. Min Act: -0.1700
Data Index: 4839515 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7568. Min Act: -0.1700
Data Index: 614444 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0381. Min Range: -5.0381
Max Act: 4.7256. Min Act: -0.1700
Data Index: 1141278 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19