Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.7752. Min Act: -0.1700
Data Index: 3215124 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.7127. Min Act: -0.1700
Data Index: 6003895 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.7127. Min Act: -0.1700
Data Index: 2655454 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.7440. Min Act: -0.1700
Data Index: 3962428 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.7127. Min Act: -0.1700
Data Index: 7468545 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6815. Min Act: -0.1700
Data Index: 1144582 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6815. Min Act: -0.1700
Data Index: 6923363 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6815. Min Act: -0.1700
Data Index: 6271077 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6502. Min Act: -0.1700
Data Index: 14320 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6502. Min Act: -0.1700
Data Index: 1254166 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6502. Min Act: -0.1700
Data Index: 422821 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5877. Min Act: -0.1700
Data Index: 2243112 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.6190. Min Act: -0.1700
Data Index: 4379329 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5877. Min Act: -0.1700
Data Index: 39857 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5877. Min Act: -0.1700
Data Index: 567341 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5252. Min Act: -0.1700
Data Index: 8082082 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5877. Min Act: -0.1700
Data Index: 3218674 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5252. Min Act: -0.1700
Data Index: 3137633 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5252. Min Act: -0.1700
Data Index: 8387151 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7752. Min Range: -4.7752
Max Act: 4.5252. Min Act: -0.1700
Data Index: 725892 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19