Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5016 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.2702. Min Act: -0.1700
Data Index: 2135084 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0971. Min Act: -0.1700
Data Index: 263695 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0814. Min Act: -0.1700
Data Index: 585183 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0814. Min Act: -0.1700
Data Index: 1102203 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0498. Min Act: -0.1700
Data Index: 3874514 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0340. Min Act: -0.1700
Data Index: 8140939 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0340. Min Act: -0.1700
Data Index: 3643523 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0024. Min Act: -0.1700
Data Index: 3960717 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 4578767 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 1278822 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 6908522 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 8524287 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9708. Min Act: -0.1700
Data Index: 6692658 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 8128887 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 6290940 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9550. Min Act: -0.1700
Data Index: 6860626 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9392. Min Act: -0.1700
Data Index: 276963 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9392. Min Act: -0.1700
Data Index: 1496247 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9392. Min Act: -0.1700
Data Index: 5841254 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9233. Min Act: -0.1700
Data Index: 3045311 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19