Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5413 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.3335. Min Act: -0.1700
Data Index: 6147380 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.2710. Min Act: -0.1700
Data Index: 1233229 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.2710. Min Act: -0.1700
Data Index: 8076259 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.2085. Min Act: -0.1700
Data Index: 290122 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1773. Min Act: -0.1700
Data Index: 6858195 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.2085. Min Act: -0.1700
Data Index: 3991777 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1773. Min Act: -0.1700
Data Index: 4289424 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1460. Min Act: -0.1700
Data Index: 1283487 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1460. Min Act: -0.1700
Data Index: 4701749 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1460. Min Act: -0.1700
Data Index: 575572 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1460. Min Act: -0.1700
Data Index: 4815787 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.0835. Min Act: -0.1700
Data Index: 8184475 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1148. Min Act: -0.1700
Data Index: 7224443 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1148. Min Act: -0.1700
Data Index: 6173746 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1148. Min Act: -0.1700
Data Index: 4171293 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1148. Min Act: -0.1700
Data Index: 6300163 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.1148. Min Act: -0.1700
Data Index: 3737425 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.0835. Min Act: -0.1700
Data Index: 292112 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.0835. Min Act: -0.1700
Data Index: 3761528 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3335. Min Range: -5.3335
Max Act: 5.0835. Min Act: -0.1700
Data Index: 3836437 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19