Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5229 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.6009. Min Act: -0.1700
Data Index: 1153334 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.5383. Min Act: -0.1700
Data Index: 2123241 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.5070. Min Act: -0.1700
Data Index: 4311123 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.5070. Min Act: -0.1700
Data Index: 3138576 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.5227. Min Act: -0.1700
Data Index: 4915943 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4913. Min Act: -0.1700
Data Index: 2394444 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4757. Min Act: -0.1700
Data Index: 994288 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4600. Min Act: -0.1700
Data Index: 3205074 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4443. Min Act: -0.1700
Data Index: 5423202 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4443. Min Act: -0.1700
Data Index: 3195506 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4443. Min Act: -0.1700
Data Index: 3037313 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4443. Min Act: -0.1700
Data Index: 8231046 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4130. Min Act: -0.1700
Data Index: 2309549 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4130. Min Act: -0.1700
Data Index: 1101055 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.4287. Min Act: -0.1700
Data Index: 2388936 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.3973. Min Act: -0.1700
Data Index: 3520134 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.3973. Min Act: -0.1700
Data Index: 600832 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.3973. Min Act: -0.1700
Data Index: 636739 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.3816. Min Act: -0.1700
Data Index: 7480874 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6009. Min Range: -3.6009
Max Act: 3.3659. Min Act: -0.1700
Data Index: 4401171 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19