Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1208 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.5088. Min Act: -0.1700
Data Index: 5775435 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.4150. Min Act: -0.1700
Data Index: 320808 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.2588. Min Act: -0.1700
Data Index: 5596886 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.0713. Min Act: -0.1700
Data Index: 4757260 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5088. Min Range: -7.5088
Max Act: 7.0088. Min Act: -0.1700
Data Index: 6963020 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.8838. Min Act: -0.1700
Data Index: 8473606 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.8838. Min Act: -0.1700
Data Index: 2387515 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 4934314 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 7490105 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 8462077 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.7900. Min Act: -0.1700
Data Index: 3436822 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 3787765 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.7900. Min Act: -0.1700
Data Index: 4017034 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.7900. Min Act: -0.1700
Data Index: 2853712 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.7588. Min Act: -0.1700
Data Index: 7186833 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.7900. Min Act: -0.1700
Data Index: 7638685 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.7275. Min Act: -0.1700
Data Index: 7861097 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.6963. Min Act: -0.1700
Data Index: 7861979 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.6963. Min Act: -0.1700
Data Index: 2589313 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5088. Min Range: -7.5088
Max Act: 6.6963. Min Act: -0.1700
Data Index: 3787768 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19