Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0065. Min Range: -7.0065
Max Act: 7.0065. Min Act: -0.1700
Data Index: 1530314 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.8190. Min Act: -0.1700
Data Index: 3069498 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6940. Min Act: -0.1700
Data Index: 651752 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6628. Min Act: -0.1700
Data Index: 3411479 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6315. Min Act: -0.1700
Data Index: 7907998 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6315. Min Act: -0.1700
Data Index: 5095107 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6003. Min Act: -0.1700
Data Index: 3039643 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6315. Min Act: -0.1700
Data Index: 1896553 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6003. Min Act: -0.1700
Data Index: 6520984 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6003. Min Act: -0.1700
Data Index: 4593404 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6003. Min Act: -0.1700
Data Index: 4134253 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6003. Min Act: -0.1700
Data Index: 3039642 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.6003. Min Act: -0.1700
Data Index: 2118848 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5690. Min Act: -0.1700
Data Index: 2321606 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5690. Min Act: -0.1700
Data Index: 5871281 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5690. Min Act: -0.1700
Data Index: 5095108 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5065. Min Act: -0.1700
Data Index: 5908614 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5065. Min Act: -0.1700
Data Index: 492000 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5378. Min Act: -0.1700
Data Index: 4742465 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0065. Min Range: -7.0065
Max Act: 6.5065. Min Act: -0.1700
Data Index: 4134256 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19