Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 88 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3184. Min Range: -5.3184
Max Act: 5.3184. Min Act: -0.1700
Data Index: 5541523 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.9122. Min Act: -0.1700
Data Index: 3095795 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.8497. Min Act: -0.1700
Data Index: 3644534 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.6934. Min Act: -0.1700
Data Index: 4441784 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.6309. Min Act: -0.1700
Data Index: 809324 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.5997. Min Act: -0.1700
Data Index: 2018914 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.5997. Min Act: -0.1700
Data Index: 8204128 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.5372. Min Act: -0.1700
Data Index: 2988132 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.5684. Min Act: -0.1700
Data Index: 4687374 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.4747. Min Act: -0.1696
Data Index: 8600946 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.4122. Min Act: -0.1700
Data Index: 6868503 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.3497. Min Act: -0.1700
Data Index: 602141 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.4122. Min Act: -0.1700
Data Index: 629209 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.3184. Min Act: -0.1700
Data Index: 2749568 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.3497. Min Act: -0.1700
Data Index: 6291066 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.3184. Min Act: -0.1700
Data Index: 4401718 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.3497. Min Act: -0.1700
Data Index: 7057032 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.3497. Min Act: -0.1700
Data Index: 6380057 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.2872. Min Act: -0.1700
Data Index: 2897360 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3184. Min Range: -5.3184
Max Act: 4.2872. Min Act: -0.1700
Data Index: 4411603 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19