Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.5393. Min Act: -0.1700
Data Index: 8334688 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.2580. Min Act: -0.1700
Data Index: 2909262 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5393. Min Range: -5.5393
Max Act: 5.1018. Min Act: -0.1700
Data Index: 3105944 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 6071689 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 458463 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.9768. Min Act: -0.1700
Data Index: 3905428 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.9455. Min Act: -0.1700
Data Index: 3382353 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.9143. Min Act: -0.1700
Data Index: 5674763 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8830. Min Act: -0.1700
Data Index: 4999359 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8518. Min Act: -0.1700
Data Index: 712184 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8518. Min Act: -0.1700
Data Index: 3954201 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8518. Min Act: -0.1700
Data Index: 4053854 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8518. Min Act: -0.1700
Data Index: 8415730 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8205. Min Act: -0.1700
Data Index: 7624690 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.8205. Min Act: -0.1700
Data Index: 4907655 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.7893. Min Act: -0.1700
Data Index: 5745817 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.7580. Min Act: -0.1700
Data Index: 2536587 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.7580. Min Act: -0.1700
Data Index: 3185452 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.7268. Min Act: -0.1700
Data Index: 3909341 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5393. Min Range: -5.5393
Max Act: 4.7268. Min Act: -0.1700
Data Index: 7658246 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19