Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.9532. Min Act: -0.1700
Data Index: 5728011 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.8907. Min Act: -0.1700
Data Index: 5886039 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.8907. Min Act: -0.1700
Data Index: 7961745 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.8282. Min Act: -0.1700
Data Index: 6381855 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2975862 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.7969. Min Act: -0.1700
Data Index: 659716 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.7657. Min Act: -0.1700
Data Index: 8106977 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.7344. Min Act: -0.1700
Data Index: 5805657 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.7032. Min Act: -0.1700
Data Index: 4221128 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6719. Min Act: -0.1700
Data Index: 8784645 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6719. Min Act: -0.1700
Data Index: 4945083 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6719. Min Act: -0.1700
Data Index: 3400764 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6719. Min Act: -0.1700
Data Index: 4822591 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6407. Min Act: -0.1700
Data Index: 5805660 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3886605 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6407. Min Act: -0.1700
Data Index: 8822073 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6407. Min Act: -0.1700
Data Index: 8271401 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6094. Min Act: -0.1700
Data Index: 3271564 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3087354 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9532. Min Range: -5.9532
Max Act: 5.6407. Min Act: -0.1700
Data Index: 600187 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19