Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4107. Min Range: -2.4107
Max Act: 2.4107. Min Act: -0.1700
Data Index: 2962780 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4107. Min Range: -2.4107
Max Act: 2.1636. Min Act: -0.1700
Data Index: 2962782 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4107. Min Range: -2.4107
Max Act: 2.1469. Min Act: -0.1700
Data Index: 2962781 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4107. Min Range: -2.4107
Max Act: 2.0464. Min Act: -0.1700
Data Index: 1278230 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4107. Min Range: -2.4107
Max Act: 2.0633. Min Act: -0.1700
Data Index: 7155252 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4107. Min Range: -2.4107
Max Act: 2.0127. Min Act: -0.1700
Data Index: 6553051 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9789. Min Act: -0.1700
Data Index: 4879701 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9789. Min Act: -0.1700
Data Index: 6169244 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9958. Min Act: -0.1700
Data Index: 3344491 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9789. Min Act: -0.1700
Data Index: 1453014 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9620. Min Act: -0.1700
Data Index: 5938443 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9620. Min Act: -0.1700
Data Index: 8306300 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9789. Min Act: -0.1700
Data Index: 5099839 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9789. Min Act: -0.1700
Data Index: 2976701 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9620. Min Act: -0.1700
Data Index: 6569306 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9620. Min Act: -0.1700
Data Index: 7848585 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9450. Min Act: -0.1700
Data Index: 204521 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9450. Min Act: -0.1700
Data Index: 1421115 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9450. Min Act: -0.1700
Data Index: 347617 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4107. Min Range: -2.4107
Max Act: 1.9450. Min Act: -0.1700
Data Index: 866890 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19