Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2320 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.2692. Min Act: -0.1700
Data Index: 8130086 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.2692. Min Act: -0.1700
Data Index: 1855042 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.2380. Min Act: -0.1700
Data Index: 4130696 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.2067. Min Act: -0.1700
Data Index: 2313275 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1755. Min Act: -0.1700
Data Index: 2747058 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1755. Min Act: -0.1700
Data Index: 8228346 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1755. Min Act: -0.1700
Data Index: 3352319 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1755. Min Act: -0.1700
Data Index: 3796843 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1755. Min Act: -0.1700
Data Index: 1723717 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1755. Min Act: -0.1700
Data Index: 2330101 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 5958375 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 5936561 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 5701609 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 5555669 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1130. Min Act: -0.1700
Data Index: 5088837 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 4668561 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 4641749 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1130. Min Act: -0.1700
Data Index: 4285762 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 4216069 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2692. Min Range: -5.2692
Max Act: 5.1442. Min Act: -0.1700
Data Index: 156840 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19