Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.1341. Min Act: -0.1700
Data Index: 4824758 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0671. Min Act: -0.1699
Data Index: 594829 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0671. Min Act: -0.1695
Data Index: 2641527 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0587. Min Act: -0.1698
Data Index: 6386596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0419. Min Act: -0.1700
Data Index: 7621849 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0250. Min Act: -0.1700
Data Index: 8399284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1341. Min Range: -2.1341
Max Act: 2.0250. Min Act: -0.1700
Data Index: 2828379 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9828. Min Act: -0.1698
Data Index: 8114691 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9912. Min Act: -0.1700
Data Index: 2024520 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9658. Min Act: -0.1700
Data Index: 4478214 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9404. Min Act: -0.1695
Data Index: 3903776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9489. Min Act: -0.1699
Data Index: 256518 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9404. Min Act: -0.1700
Data Index: 4032060 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9319. Min Act: -0.1700
Data Index: 2024519 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9319. Min Act: -0.1700
Data Index: 1615734 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9234. Min Act: -0.1700
Data Index: 350704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9234. Min Act: -0.1700
Data Index: 7251282 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9063. Min Act: -0.1700
Data Index: 1233829 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.9063. Min Act: -0.1699
Data Index: 6090106 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1341. Min Range: -2.1341
Max Act: 1.8978. Min Act: -0.1700
Data Index: 4745428 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19