Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.4658. Min Act: -0.1700
Data Index: 1542091 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.4033. Min Act: -0.1700
Data Index: 2916470 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3408. Min Act: -0.1700
Data Index: 7164318 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3408. Min Act: -0.1700
Data Index: 5492442 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3096. Min Act: -0.1700
Data Index: 4389673 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3096. Min Act: -0.1700
Data Index: 6312338 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.3096. Min Act: -0.1700
Data Index: 2316588 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2783. Min Act: -0.1700
Data Index: 5825545 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2783. Min Act: -0.1700
Data Index: 5528306 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2783. Min Act: -0.1700
Data Index: 2802253 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2471. Min Act: -0.1700
Data Index: 3769688 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2471. Min Act: -0.1700
Data Index: 3215783 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2471. Min Act: -0.1700
Data Index: 1905540 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2471. Min Act: -0.1700
Data Index: 4881145 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2471. Min Act: -0.1700
Data Index: 242760 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 4010480 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 4537113 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 2134903 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 6855893 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4658. Min Range: -4.4658
Max Act: 4.2158. Min Act: -0.1700
Data Index: 7527324 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19