Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.8843. Min Act: -0.1700
Data Index: 2920210 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.7593. Min Act: -0.1700
Data Index: 5710538 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.7281. Min Act: -0.1700
Data Index: 7900908 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.6968. Min Act: -0.1700
Data Index: 2975149 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.6656. Min Act: -0.1700
Data Index: 3143783 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.6343. Min Act: -0.1700
Data Index: 7114392 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.6343. Min Act: -0.1700
Data Index: 2501369 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.6343. Min Act: -0.1700
Data Index: 224578 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.6031. Min Act: -0.1700
Data Index: 6867620 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5718. Min Act: -0.1700
Data Index: 6627484 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5718. Min Act: -0.1700
Data Index: 6544437 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5093. Min Act: -0.1700
Data Index: 4106544 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5406. Min Act: -0.1700
Data Index: 2245065 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.4781. Min Act: -0.1700
Data Index: 6146742 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5093. Min Act: -0.1700
Data Index: 1907722 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5093. Min Act: -0.1700
Data Index: 3497447 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5093. Min Act: -0.1700
Data Index: 6203790 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5093. Min Act: -0.1700
Data Index: 5957273 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.5093. Min Act: -0.1700
Data Index: 4297586 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8843. Min Range: -5.8843
Max Act: 5.4781. Min Act: -0.1700
Data Index: 4787488 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19