Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.7937. Min Act: -0.1700
Data Index: 656659 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.7937. Min Act: -0.1700
Data Index: 2206423 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.7937. Min Act: -0.1700
Data Index: 1259536 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.7000. Min Act: -0.1700
Data Index: 1259535 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.6687. Min Act: -0.1700
Data Index: 517594 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.6062. Min Act: -0.1700
Data Index: 6092816 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.6062. Min Act: -0.1700
Data Index: 8706076 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.6062. Min Act: -0.1700
Data Index: 4764099 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.5750. Min Act: -0.1700
Data Index: 7872023 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.5750. Min Act: -0.1700
Data Index: 940227 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.5437. Min Act: -0.1700
Data Index: 418327 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.5437. Min Act: -0.1700
Data Index: 1540429 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.5437. Min Act: -0.1700
Data Index: 7663822 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.5125. Min Act: -0.1700
Data Index: 7791858 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.4812. Min Act: -0.1700
Data Index: 4489085 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.4500. Min Act: -0.1700
Data Index: 7349090 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.4500. Min Act: -0.1700
Data Index: 1121123 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.4500. Min Act: -0.1700
Data Index: 6794142 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.4187. Min Act: -0.1700
Data Index: 3854649 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7937. Min Range: -6.7937
Max Act: 6.3875. Min Act: -0.1700
Data Index: 169049 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19