Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.6362. Min Act: -0.1700
Data Index: 3126787 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.6050. Min Act: -0.1700
Data Index: 4557910 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.4800. Min Act: -0.1700
Data Index: 710278 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.4800. Min Act: -0.1700
Data Index: 4073659 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1911024 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.4175. Min Act: -0.1700
Data Index: 2844376 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.3862. Min Act: -0.1700
Data Index: 6592555 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.3862. Min Act: -0.1700
Data Index: 6651916 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.3862. Min Act: -0.1700
Data Index: 8688938 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.3550. Min Act: -0.1700
Data Index: 679478 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.3237. Min Act: -0.1700
Data Index: 2234450 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.1675. Min Act: -0.1700
Data Index: 1920338 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.1675. Min Act: -0.1700
Data Index: 7395462 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.1362. Min Act: -0.1700
Data Index: 8799538 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.1050. Min Act: -0.1700
Data Index: 6974704 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.0737. Min Act: -0.1700
Data Index: 7263867 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.1050. Min Act: -0.1700
Data Index: 7241825 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.0737. Min Act: -0.1700
Data Index: 4072119 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.1050. Min Act: -0.1700
Data Index: 3556073 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6362. Min Range: -6.6362
Max Act: 6.0425. Min Act: -0.1700
Data Index: 88542 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19