Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.3901. Min Act: -0.1700
Data Index: 1863686 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.3588. Min Act: -0.1700
Data Index: 608553 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.3276. Min Act: -0.1700
Data Index: 5915079 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.2963. Min Act: -0.1700
Data Index: 4987307 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.2651. Min Act: -0.1700
Data Index: 3899776 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.2651. Min Act: -0.1700
Data Index: 5591426 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.2338. Min Act: -0.1700
Data Index: 4073891 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1713. Min Act: -0.1700
Data Index: 1078964 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.2026. Min Act: -0.1700
Data Index: 60005 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1401. Min Act: -0.1700
Data Index: 2594101 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1401. Min Act: -0.1700
Data Index: 426017 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1401. Min Act: -0.1700
Data Index: 6549183 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1401. Min Act: -0.1700
Data Index: 4296518 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.0776. Min Act: -0.1698
Data Index: 1738941 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.0776. Min Act: -0.1700
Data Index: 5196224 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1088. Min Act: -0.1700
Data Index: 2679883 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1088. Min Act: -0.1700
Data Index: 6964979 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.1088. Min Act: -0.1700
Data Index: 7042275 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.0776. Min Act: -0.1700
Data Index: 2781936 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3901. Min Range: -5.3901
Max Act: 5.0776. Min Act: -0.1700
Data Index: 4173258 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19