Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2427 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.8781. Min Act: -0.1700
Data Index: 3708370 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.7843. Min Act: -0.1700
Data Index: 4314417 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.5031. Min Act: -0.1700
Data Index: 5416705 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4093. Min Act: -0.1700
Data Index: 6603141 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.4406. Min Act: -0.1700
Data Index: 8804177 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.3468. Min Act: -0.1700
Data Index: 96221 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.3781. Min Act: -0.1700
Data Index: 5833045 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.3156. Min Act: -0.1700
Data Index: 8412386 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.2843. Min Act: -0.1700
Data Index: 2129103 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.2843. Min Act: -0.1700
Data Index: 813762 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.2843. Min Act: -0.1700
Data Index: 359402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.2218. Min Act: -0.1700
Data Index: 5459746 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.2218. Min Act: -0.1700
Data Index: 4534876 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.1906. Min Act: -0.1700
Data Index: 6763588 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.1906. Min Act: -0.1700
Data Index: 561848 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.2218. Min Act: -0.1700
Data Index: 8008346 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.1281. Min Act: -0.1700
Data Index: 4192786 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.0968. Min Act: -0.1700
Data Index: 4441350 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.1593. Min Act: -0.1700
Data Index: 5267766 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8781. Min Range: -5.8781
Max Act: 5.1281. Min Act: -0.1700
Data Index: 2803546 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19