Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3584. Min Range: -8.3584
Max Act: 8.3584. Min Act: -0.1700
Data Index: 2386515 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.9834. Min Act: -0.1700
Data Index: 8548996 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.9834. Min Act: -0.1700
Data Index: 4069284 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.9209. Min Act: -0.1700
Data Index: 7339942 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.9209. Min Act: -0.1700
Data Index: 3974550 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.8584. Min Act: -0.1700
Data Index: 7053383 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.8584. Min Act: -0.1700
Data Index: 7905871 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.8584. Min Act: -0.1700
Data Index: 3600112 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.8584. Min Act: -0.1700
Data Index: 4598729 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7959. Min Act: -0.1700
Data Index: 1357823 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7959. Min Act: -0.1700
Data Index: 3410756 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7334. Min Act: -0.1700
Data Index: 8331673 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7959. Min Act: -0.1700
Data Index: 8248310 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7959. Min Act: -0.1700
Data Index: 597579 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7334. Min Act: -0.1700
Data Index: 1380525 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.7334. Min Act: -0.1700
Data Index: 5150409 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.6709. Min Act: -0.1700
Data Index: 5217327 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.6709. Min Act: -0.1700
Data Index: 7015006 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.6709. Min Act: -0.1700
Data Index: 7264922 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3584. Min Range: -8.3584
Max Act: 7.6709. Min Act: -0.1700
Data Index: 4478725 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19