Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1447 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.5225. Min Act: -0.1700
Data Index: 3180476 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3350. Min Act: -0.1700
Data Index: 1942351 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3038. Min Act: -0.1700
Data Index: 2775631 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2725. Min Act: -0.1700
Data Index: 138419 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1788. Min Act: -0.1700
Data Index: 2802248 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2100. Min Act: -0.1700
Data Index: 3757601 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1788. Min Act: -0.1700
Data Index: 804122 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1788. Min Act: -0.1700
Data Index: 1377202 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2100. Min Act: -0.1700
Data Index: 8442886 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 4838198 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 1336412 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1163. Min Act: -0.1700
Data Index: 4795305 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 4567530 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 8670510 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 1050067 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 7705598 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 5514254 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 5020900 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 1368904 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.1475. Min Act: -0.1700
Data Index: 2072583 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19