Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.4975. Min Act: -0.1700
Data Index: 399489 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.4037. Min Act: -0.1700
Data Index: 6811420 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.3412. Min Act: -0.1700
Data Index: 849699 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.2475. Min Act: -0.1700
Data Index: 4493169 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.1225. Min Act: -0.1700
Data Index: 3742612 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0912. Min Act: -0.1700
Data Index: 4031265 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0600. Min Act: -0.1700
Data Index: 5234161 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0600. Min Act: -0.1700
Data Index: 3360894 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0600. Min Act: -0.1700
Data Index: 1404167 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0600. Min Act: -0.1700
Data Index: 89097 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0600. Min Act: -0.1700
Data Index: 6312497 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4975. Min Range: -6.4975
Max Act: 6.0287. Min Act: -0.1700
Data Index: 2062694 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9975. Min Act: -0.1700
Data Index: 7757045 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9975. Min Act: -0.1700
Data Index: 4542801 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9662. Min Act: -0.1700
Data Index: 5037359 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2638807 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9350. Min Act: -0.1700
Data Index: 4748111 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9350. Min Act: -0.1700
Data Index: 5547401 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9350. Min Act: -0.1700
Data Index: 702130 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4975. Min Range: -6.4975
Max Act: 5.9350. Min Act: -0.1700
Data Index: 5344604 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19