Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.9290. Min Act: -0.1700
Data Index: 2870030 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.8665. Min Act: -0.1700
Data Index: 5664695 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.8040. Min Act: -0.1700
Data Index: 4500758 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.8040. Min Act: -0.1700
Data Index: 1181642 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.8040. Min Act: -0.1700
Data Index: 5590991 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.7415. Min Act: -0.1700
Data Index: 6631926 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.5540. Min Act: -0.1700
Data Index: 1590830 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.6165. Min Act: -0.1700
Data Index: 1501744 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.6165. Min Act: -0.1700
Data Index: 523151 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.5540. Min Act: -0.1700
Data Index: 2443381 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 3331279 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 2901790 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 7142614 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 5333039 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 2243437 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 2244248 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4915. Min Act: -0.1700
Data Index: 6145642 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4290. Min Act: -0.1700
Data Index: 2166490 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4290. Min Act: -0.1700
Data Index: 5005530 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9290. Min Range: -9.9290
Max Act: 9.4290. Min Act: -0.1700
Data Index: 5900201 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19