Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6309 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6552. Min Act: -0.1700
Data Index: 3313893 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6552. Min Act: -0.1700
Data Index: 320878 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.6240. Min Act: -0.1700
Data Index: 7643869 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5927. Min Act: -0.1700
Data Index: 6761369 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5615. Min Act: -0.1700
Data Index: 4236500 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5927. Min Act: -0.1700
Data Index: 2159590 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5615. Min Act: -0.1700
Data Index: 7780632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5615. Min Act: -0.1700
Data Index: 306871 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 7246552 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 7544881 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4990. Min Act: -0.1700
Data Index: 972917 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4990. Min Act: -0.1700
Data Index: 2771077 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4990. Min Act: -0.1700
Data Index: 6500703 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.5302. Min Act: -0.1700
Data Index: 1660374 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4677. Min Act: -0.1700
Data Index: 5889457 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4677. Min Act: -0.1700
Data Index: 4355217 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4677. Min Act: -0.1700
Data Index: 583169 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4365. Min Act: -0.1700
Data Index: 4205321 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4365. Min Act: -0.1700
Data Index: 744073 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6552. Min Range: -4.6552
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2954749 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19