Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0780. Min Range: -4.0780
Max Act: 4.0780. Min Act: -0.1700
Data Index: 10290 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0780. Min Range: -4.0780
Max Act: 4.0155. Min Act: -0.1700
Data Index: 7973620 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9842. Min Act: -0.1700
Data Index: 4052757 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9530. Min Act: -0.1700
Data Index: 6719859 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9530. Min Act: -0.1700
Data Index: 1394216 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 4185830 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 6627221 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 1045047 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 7119697 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 5409949 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 3521224 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 6470014 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 2066555 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 8461200 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 8461198 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 5811510 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 8070195 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8904. Min Act: -0.1700
Data Index: 4841479 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8592. Min Act: -0.1700
Data Index: 6097377 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.8592. Min Act: -0.1700
Data Index: 2169214 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19