Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 598 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5462. Min Range: -8.5462
Max Act: 8.5462. Min Act: -0.1700
Data Index: 5467451 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5462. Min Range: -8.5462
Max Act: 8.2962. Min Act: -0.1700
Data Index: 1636259 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5462. Min Range: -8.5462
Max Act: 8.2337. Min Act: -0.1700
Data Index: 2715787 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5462. Min Range: -8.5462
Max Act: 8.1712. Min Act: -0.1700
Data Index: 4093175 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5462. Min Range: -8.5462
Max Act: 8.1087. Min Act: -0.1700
Data Index: 3823339 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.9837. Min Act: -0.1700
Data Index: 5487503 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.9212. Min Act: -0.1700
Data Index: 8662770 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.9212. Min Act: -0.1700
Data Index: 1380820 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.9837. Min Act: -0.1700
Data Index: 6138424 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.8587. Min Act: -0.1700
Data Index: 4390122 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.8587. Min Act: -0.1700
Data Index: 1992860 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.8587. Min Act: -0.1700
Data Index: 7783411 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.7962. Min Act: -0.1700
Data Index: 2700095 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.8587. Min Act: -0.1700
Data Index: 738457 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.8587. Min Act: -0.1700
Data Index: 7370662 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.7962. Min Act: -0.1700
Data Index: 4597503 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.7337. Min Act: -0.1700
Data Index: 828506 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.7962. Min Act: -0.1700
Data Index: 4950129 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.7962. Min Act: -0.1700
Data Index: 1229386 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5462. Min Range: -8.5462
Max Act: 7.7962. Min Act: -0.1700
Data Index: 224489 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19