Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1902 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.2259. Min Act: -0.1700
Data Index: 5419404 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1321. Min Act: -0.1700
Data Index: 1372845 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1009. Min Act: -0.1700
Data Index: 568058 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1321. Min Act: -0.1700
Data Index: 5485048 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1009. Min Act: -0.1700
Data Index: 932095 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1009. Min Act: -0.1700
Data Index: 6076849 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0696. Min Act: -0.1700
Data Index: 5987466 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.1009. Min Act: -0.1700
Data Index: 1617738 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0696. Min Act: -0.1700
Data Index: 5324589 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2220616 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0696. Min Act: -0.1700
Data Index: 8556220 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0696. Min Act: -0.1700
Data Index: 4140140 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 3555098 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2457702 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 8680590 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 1256810 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0071. Min Act: -0.1700
Data Index: 6299653 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 1309902 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0384. Min Act: -0.1700
Data Index: 1321622 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2259. Min Range: -5.2259
Max Act: 5.0071. Min Act: -0.1700
Data Index: 4978235 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19