Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0674. Min Range: -5.0674
Max Act: 5.0674. Min Act: -0.1700
Data Index: 2428038 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0674. Min Range: -5.0674
Max Act: 5.0361. Min Act: -0.1700
Data Index: 8687460 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.9424. Min Act: -0.1700
Data Index: 5627784 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.9111. Min Act: -0.1700
Data Index: 7814793 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.9111. Min Act: -0.1700
Data Index: 1599901 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.8486. Min Act: -0.1700
Data Index: 7865892 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.8174. Min Act: -0.1700
Data Index: 248759 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7861. Min Act: -0.1700
Data Index: 6949184 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7861. Min Act: -0.1700
Data Index: 889758 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7549. Min Act: -0.1700
Data Index: 6316079 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7236. Min Act: -0.1700
Data Index: 6312367 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7549. Min Act: -0.1700
Data Index: 7825432 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7236. Min Act: -0.1700
Data Index: 8691164 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6924. Min Act: -0.1700
Data Index: 6394096 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6924. Min Act: -0.1700
Data Index: 4424441 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6924. Min Act: -0.1700
Data Index: 1926580 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6924. Min Act: -0.1700
Data Index: 3367017 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6611. Min Act: -0.1700
Data Index: 3761783 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6611. Min Act: -0.1700
Data Index: 5212251 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5907572 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19