Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1417. Min Range: -6.1417
Max Act: 6.1417. Min Act: -0.1700
Data Index: 3839400 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1417. Min Range: -6.1417
Max Act: 6.1105. Min Act: -0.1700
Data Index: 3762886 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1417. Min Range: -6.1417
Max Act: 6.0792. Min Act: -0.1700
Data Index: 3240638 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1417. Min Range: -6.1417
Max Act: 6.0480. Min Act: -0.1700
Data Index: 4760094 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1417. Min Range: -6.1417
Max Act: 6.0167. Min Act: -0.1700
Data Index: 2610904 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.9855. Min Act: -0.1698
Data Index: 7768101 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.9230. Min Act: -0.1700
Data Index: 3125129 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.9230. Min Act: -0.1700
Data Index: 3839401 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.9230. Min Act: -0.1699
Data Index: 3125122 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.9542. Min Act: -0.1700
Data Index: 1341365 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.8605. Min Act: -0.1700
Data Index: 4821755 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.8605. Min Act: -0.1700
Data Index: 3741869 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.8605. Min Act: -0.1700
Data Index: 4618811 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.8292. Min Act: -0.1700
Data Index: 3839402 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.8292. Min Act: -0.1700
Data Index: 483550 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.8292. Min Act: -0.1700
Data Index: 2430102 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.7980. Min Act: -0.1700
Data Index: 1125104 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.7980. Min Act: -0.1699
Data Index: 4835810 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.7980. Min Act: -0.1700
Data Index: 7820261 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1417. Min Range: -6.1417
Max Act: 5.7980. Min Act: -0.1700
Data Index: 1085949 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19