Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.9686. Min Act: -0.1700
Data Index: 7620014 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.5936. Min Act: -0.1700
Data Index: 1628144 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.5311. Min Act: -0.1700
Data Index: 6589367 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.5311. Min Act: -0.1700
Data Index: 5859658 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.4061. Min Act: -0.1700
Data Index: 1632310 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.3436. Min Act: -0.1700
Data Index: 952899 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.4061. Min Act: -0.1700
Data Index: 8538846 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.4061. Min Act: -0.1700
Data Index: 6464839 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.3749. Min Act: -0.1700
Data Index: 4578968 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.3124. Min Act: -0.1700
Data Index: 7057602 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.3124. Min Act: -0.1700
Data Index: 8616337 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2499. Min Act: -0.1700
Data Index: 5176460 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2499. Min Act: -0.1700
Data Index: 2090787 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2499. Min Act: -0.1700
Data Index: 6179498 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2499. Min Act: -0.1700
Data Index: 371487 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2499. Min Act: -0.1700
Data Index: 7144226 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2186. Min Act: -0.1700
Data Index: 45155 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2186. Min Act: -0.1700
Data Index: 1919686 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.2186. Min Act: -0.1700
Data Index: 7113085 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9686. Min Range: -6.9686
Max Act: 6.1874. Min Act: -0.1700
Data Index: 3516546 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19