Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1757. Min Range: -5.1757
Max Act: 5.1757. Min Act: -0.1700
Data Index: 2185918 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1757. Min Range: -5.1757
Max Act: 5.0820. Min Act: -0.1700
Data Index: 2022619 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9882. Min Act: -0.1700
Data Index: 7782382 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1757. Min Range: -5.1757
Max Act: 5.0195. Min Act: -0.1700
Data Index: 2185906 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1757. Min Range: -5.1757
Max Act: 5.0195. Min Act: -0.1700
Data Index: 1636247 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9882. Min Act: -0.1700
Data Index: 8296814 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1757. Min Range: -5.1757
Max Act: 5.0195. Min Act: -0.1700
Data Index: 4157956 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9570. Min Act: -0.1700
Data Index: 5456542 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9257. Min Act: -0.1700
Data Index: 7870228 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8945. Min Act: -0.1700
Data Index: 8453624 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9257. Min Act: -0.1700
Data Index: 2992504 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9257. Min Act: -0.1700
Data Index: 7247606 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9257. Min Act: -0.1700
Data Index: 1588364 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.9257. Min Act: -0.1700
Data Index: 7391340 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8945. Min Act: -0.1700
Data Index: 5398004 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8632. Min Act: -0.1700
Data Index: 4456918 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8945. Min Act: -0.1700
Data Index: 6336904 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4368836 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8632. Min Act: -0.1700
Data Index: 3622414 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1757. Min Range: -5.1757
Max Act: 4.8945. Min Act: -0.1700
Data Index: 6261863 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19