Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.5886. Min Act: -0.1700
Data Index: 5857766 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.4636. Min Act: -0.1700
Data Index: 111760 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.4636. Min Act: -0.1700
Data Index: 5557515 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.4324. Min Act: -0.1700
Data Index: 4743666 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.3699. Min Act: -0.1700
Data Index: 2319046 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.4011. Min Act: -0.1700
Data Index: 5392048 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.3386. Min Act: -0.1700
Data Index: 545602 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.3386. Min Act: -0.1700
Data Index: 4791654 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.3386. Min Act: -0.1700
Data Index: 5881639 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2449. Min Act: -0.1700
Data Index: 8049984 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2761. Min Act: -0.1700
Data Index: 2771220 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2449. Min Act: -0.1700
Data Index: 6606604 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2449. Min Act: -0.1700
Data Index: 443099 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2136. Min Act: -0.1700
Data Index: 8132106 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2449. Min Act: -0.1700
Data Index: 8503805 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2136. Min Act: -0.1700
Data Index: 8252247 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.2136. Min Act: -0.1700
Data Index: 1175419 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.1511. Min Act: -0.1700
Data Index: 6926634 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.1824. Min Act: -0.1700
Data Index: 7974809 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5886. Min Range: -5.5886
Max Act: 5.1824. Min Act: -0.1700
Data Index: 1847006 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19