Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0187. Min Range: -3.0187
Max Act: 3.0187. Min Act: -0.1700
Data Index: 6890877 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0187. Min Range: -3.0187
Max Act: 3.0029. Min Act: -0.1700
Data Index: 4800566 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.9079. Min Act: -0.1700
Data Index: 6946182 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8603. Min Act: -0.1700
Data Index: 1275283 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8285. Min Act: -0.1700
Data Index: 893860 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8285. Min Act: -0.1700
Data Index: 1299107 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 8665358 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8444. Min Act: -0.1700
Data Index: 8050445 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 5115524 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 5998499 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.8126. Min Act: -0.1700
Data Index: 5160844 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7967. Min Act: -0.1700
Data Index: 7894770 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7808. Min Act: -0.1700
Data Index: 8670737 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7648. Min Act: -0.1700
Data Index: 1541937 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7489. Min Act: -0.1700
Data Index: 901592 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7329. Min Act: -0.1700
Data Index: 7525493 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7489. Min Act: -0.1700
Data Index: 7693549 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7489. Min Act: -0.1700
Data Index: 4281051 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7169. Min Act: -0.1700
Data Index: 5248503 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0187. Min Range: -3.0187
Max Act: 2.7329. Min Act: -0.1700
Data Index: 7907679 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19