Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1270. Min Range: -3.1270
Max Act: 3.1270. Min Act: -0.1700
Data Index: 114023 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1270. Min Range: -3.1270
Max Act: 3.0955. Min Act: -0.1700
Data Index: 4326503 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1270. Min Range: -3.1270
Max Act: 3.0797. Min Act: -0.1700
Data Index: 7381148 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1270. Min Range: -3.1270
Max Act: 3.0639. Min Act: -0.1700
Data Index: 5720366 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1270. Min Range: -3.1270
Max Act: 3.0008. Min Act: -0.1700
Data Index: 1551227 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.9691. Min Act: -0.1700
Data Index: 5877168 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.9691. Min Act: -0.1700
Data Index: 410186 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.9375. Min Act: -0.1700
Data Index: 7031655 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.9216. Min Act: -0.1700
Data Index: 8279097 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.9216. Min Act: -0.1700
Data Index: 7019622 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8899. Min Act: -0.1700
Data Index: 6855259 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8741. Min Act: -0.1700
Data Index: 134256 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8741. Min Act: -0.1700
Data Index: 5849179 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8899. Min Act: -0.1700
Data Index: 321112 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8582. Min Act: -0.1700
Data Index: 3255435 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8741. Min Act: -0.1700
Data Index: 627018 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8741. Min Act: -0.1700
Data Index: 5602633 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8582. Min Act: -0.1700
Data Index: 6167415 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8741. Min Act: -0.1700
Data Index: 8248761 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1270. Min Range: -3.1270
Max Act: 2.8741. Min Act: -0.1700
Data Index: 5027983 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19