Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.2380. Min Act: -0.1700
Data Index: 7063879 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.1442. Min Act: -0.1700
Data Index: 5016381 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.1442. Min Act: -0.1700
Data Index: 4335254 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.1442. Min Act: -0.1700
Data Index: 2316252 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.1442. Min Act: -0.1700
Data Index: 205121 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.0817. Min Act: -0.1700
Data Index: 3272190 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.0505. Min Act: -0.1700
Data Index: 732494 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.0505. Min Act: -0.1700
Data Index: 282751 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.0505. Min Act: -0.1700
Data Index: 4335244 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2380. Min Range: -7.2380
Max Act: 7.0192. Min Act: -0.1700
Data Index: 7077147 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9567. Min Act: -0.1700
Data Index: 6372221 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9880. Min Act: -0.1700
Data Index: 6068409 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9567. Min Act: -0.1700
Data Index: 2753984 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9567. Min Act: -0.1700
Data Index: 8255838 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9255. Min Act: -0.1700
Data Index: 5905446 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9255. Min Act: -0.1700
Data Index: 6536739 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9567. Min Act: -0.1700
Data Index: 4315527 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.9255. Min Act: -0.1700
Data Index: 2571541 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.8942. Min Act: -0.1700
Data Index: 8193176 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2380. Min Range: -7.2380
Max Act: 6.8317. Min Act: -0.1700
Data Index: 5827863 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19