Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6479. Min Act: -0.1700
Data Index: 719513 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6166. Min Act: -0.1700
Data Index: 5032896 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6166. Min Act: -0.1700
Data Index: 1832650 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6166. Min Act: -0.1700
Data Index: 5361804 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6166. Min Act: -0.1700
Data Index: 1769926 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 3076447 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6166. Min Act: -0.1700
Data Index: 3282713 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 6172968 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 2559469 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 6183163 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 6175409 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 622512 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 5687459 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.6166. Min Act: -0.1700
Data Index: 7921174 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 5287870 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5854. Min Act: -0.1700
Data Index: 6659964 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5541. Min Act: -0.1700
Data Index: 5709143 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5541. Min Act: -0.1700
Data Index: 4174792 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5541. Min Act: -0.1700
Data Index: 6574389 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6479. Min Range: -4.6479
Max Act: 4.5541. Min Act: -0.1700
Data Index: 4648607 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19