Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4872. Min Act: -0.1700
Data Index: 4922117 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4608. Min Act: -0.1700
Data Index: 6152353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 1273609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 1654050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 2226709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 2702359 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 3398038 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 4128535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 8546046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 5841386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 376031 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4520. Min Act: -0.1700
Data Index: 6342166 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4256. Min Act: -0.1700
Data Index: 5956439 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4256. Min Act: -0.1699
Data Index: 5318721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4080. Min Act: -0.1700
Data Index: 17645 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4080. Min Act: -0.1700
Data Index: 357804 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4080. Min Act: -0.1700
Data Index: 219402 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4080. Min Act: -0.1700
Data Index: 605651 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4080. Min Act: -0.1700
Data Index: 44981 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4872. Min Range: -1.4872
Max Act: 1.4080. Min Act: -0.1700
Data Index: 367870 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19