Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 763 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7616631 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.2621. Min Act: -0.1700
Data Index: 2162498 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.2621. Min Act: -0.1700
Data Index: 6007337 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.2621. Min Act: -0.1700
Data Index: 6336537 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.2308. Min Act: -0.1700
Data Index: 4268644 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 6360919 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 8684127 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 4167219 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 8114422 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 7003168 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 6235579 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 7407186 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.2308. Min Act: -0.1700
Data Index: 8067098 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 5977440 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 4975013 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 6209779 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 4825633 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 2152261 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1683. Min Act: -0.1700
Data Index: 3959567 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2621. Min Range: -4.2621
Max Act: 4.1371. Min Act: -0.1700
Data Index: 3602072 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19