Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1156 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.9800. Min Act: -0.1700
Data Index: 4345938 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.8238. Min Act: -0.1700
Data Index: 1259115 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.7925. Min Act: -0.1700
Data Index: 4179352 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6988. Min Act: -0.1700
Data Index: 7902765 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6988. Min Act: -0.1700
Data Index: 8098892 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6363. Min Act: -0.1700
Data Index: 1238650 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6050. Min Act: -0.1700
Data Index: 3444194 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5738. Min Act: -0.1700
Data Index: 5111338 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5738. Min Act: -0.1700
Data Index: 607469 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5738. Min Act: -0.1700
Data Index: 8520465 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6050. Min Act: -0.1700
Data Index: 7701220 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5425. Min Act: -0.1700
Data Index: 8145792 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5113. Min Act: -0.1700
Data Index: 7791514 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5425. Min Act: -0.1700
Data Index: 1664288 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5113. Min Act: -0.1700
Data Index: 4296328 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4488. Min Act: -0.1700
Data Index: 3078880 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 5954232 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 90572 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 4034168 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 2000139 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19