Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5099 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0501. Min Range: -7.0501
Max Act: 7.0501. Min Act: -0.1700
Data Index: 1494063 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.9564. Min Act: -0.1700
Data Index: 8548377 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.8939. Min Act: -0.1700
Data Index: 4195168 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7767466 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.8314. Min Act: -0.1700
Data Index: 8332097 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.7376. Min Act: -0.1700
Data Index: 6458332 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.7376. Min Act: -0.1700
Data Index: 1453782 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.7376. Min Act: -0.1700
Data Index: 3277466 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.7064. Min Act: -0.1700
Data Index: 7425208 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.7064. Min Act: -0.1700
Data Index: 6377707 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.7064. Min Act: -0.1700
Data Index: 6056616 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.6751. Min Act: -0.1700
Data Index: 748750 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.6439. Min Act: -0.1700
Data Index: 4970282 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.6439. Min Act: -0.1700
Data Index: 1561288 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.6126. Min Act: -0.1700
Data Index: 7738697 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.5814. Min Act: -0.1700
Data Index: 2038715 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.5814. Min Act: -0.1700
Data Index: 2206036 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.5814. Min Act: -0.1700
Data Index: 4882125 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.5814. Min Act: -0.1700
Data Index: 2949349 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0501. Min Range: -7.0501
Max Act: 6.5814. Min Act: -0.1700
Data Index: 8413616 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19