Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0819. Min Range: -3.0819
Max Act: 3.0819. Min Act: -0.1700
Data Index: 6993162 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0819. Min Range: -3.0819
Max Act: 3.0661. Min Act: -0.1700
Data Index: 3695683 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0819. Min Range: -3.0819
Max Act: 3.0187. Min Act: -0.1700
Data Index: 4405956 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9871. Min Act: -0.1700
Data Index: 8497036 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9555. Min Act: -0.1700
Data Index: 4058914 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9397. Min Act: -0.1700
Data Index: 3367473 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9555. Min Act: -0.1700
Data Index: 1270359 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9555. Min Act: -0.1700
Data Index: 5821588 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9397. Min Act: -0.1700
Data Index: 2628432 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9555. Min Act: -0.1700
Data Index: 3537758 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9397. Min Act: -0.1700
Data Index: 3216435 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9397. Min Act: -0.1700
Data Index: 3606019 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9238. Min Act: -0.1700
Data Index: 1577143 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9080. Min Act: -0.1700
Data Index: 3951992 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.8921. Min Act: -0.1700
Data Index: 4874979 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.8921. Min Act: -0.1700
Data Index: 7077756 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.8921. Min Act: -0.1700
Data Index: 102237 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.8921. Min Act: -0.1700
Data Index: 6554658 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9080. Min Act: -0.1700
Data Index: 2017621 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0819. Min Range: -3.0819
Max Act: 2.9080. Min Act: -0.1700
Data Index: 4911314 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19