Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 116 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.6627. Min Act: -0.1700
Data Index: 7323892 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.6002. Min Act: -0.1700
Data Index: 5187424 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.5689. Min Act: -0.1700
Data Index: 2190310 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.5377. Min Act: -0.1700
Data Index: 4786635 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 5534786 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.5064. Min Act: -0.1700
Data Index: 5771236 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.5064. Min Act: -0.1700
Data Index: 6424298 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 661554 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 7892440 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 744536 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 5162647 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 5116628 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4752. Min Act: -0.1700
Data Index: 184340 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4439. Min Act: -0.1700
Data Index: 2679498 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4439. Min Act: -0.1700
Data Index: 5047583 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4127. Min Act: -0.1700
Data Index: 7359902 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4439. Min Act: -0.1700
Data Index: 165955 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4439. Min Act: -0.1700
Data Index: 2749202 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4439. Min Act: -0.1700
Data Index: 3898473 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6627. Min Range: -4.6627
Max Act: 4.4439. Min Act: -0.1700
Data Index: 1778159 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19