Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5022 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.6940. Min Act: -0.1700
Data Index: 7432472 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.6003. Min Act: -0.1700
Data Index: 4120531 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.5378. Min Act: -0.1700
Data Index: 3052581 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.2565. Min Act: -0.1700
Data Index: 4602703 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.1940. Min Act: -0.1700
Data Index: 3866746 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.1940. Min Act: -0.1700
Data Index: 3356412 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.1628. Min Act: -0.1700
Data Index: 1707529 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.1003. Min Act: -0.1700
Data Index: 3027823 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.0690. Min Act: -0.1700
Data Index: 5187149 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.0690. Min Act: -0.1700
Data Index: 2314318 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.0690. Min Act: -0.1700
Data Index: 1235794 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6940. Min Range: -6.6940
Max Act: 6.0378. Min Act: -0.1700
Data Index: 3495858 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.9753. Min Act: -0.1700
Data Index: 6599241 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.9753. Min Act: -0.1700
Data Index: 2977086 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.9440. Min Act: -0.1700
Data Index: 1905427 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.9128. Min Act: -0.1700
Data Index: 1319612 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.9128. Min Act: -0.1700
Data Index: 4261023 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.8815. Min Act: -0.1700
Data Index: 7236374 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.8503. Min Act: -0.1700
Data Index: 1195888 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6940. Min Range: -6.6940
Max Act: 5.8815. Min Act: -0.1700
Data Index: 6782462 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19