Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.8577. Min Act: -0.1700
Data Index: 2664359 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.7639. Min Act: -0.1700
Data Index: 2146410 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.5764. Min Act: -0.1700
Data Index: 4326448 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.5452. Min Act: -0.1700
Data Index: 1423138 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.4827. Min Act: -0.1700
Data Index: 783098 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.4827. Min Act: -0.1700
Data Index: 8485591 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.4827. Min Act: -0.1700
Data Index: 2367493 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.4827. Min Act: -0.1700
Data Index: 1166404 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.4202. Min Act: -0.1700
Data Index: 7956662 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.3889. Min Act: -0.1700
Data Index: 7334329 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.3889. Min Act: -0.1700
Data Index: 5469490 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.3889. Min Act: -0.1700
Data Index: 7161746 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.3264. Min Act: -0.1700
Data Index: 3364316 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.3577. Min Act: -0.1700
Data Index: 4814201 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.3264. Min Act: -0.1700
Data Index: 5843060 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.2952. Min Act: -0.1700
Data Index: 1747851 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.2014. Min Act: -0.1700
Data Index: 7194100 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.2327. Min Act: -0.1700
Data Index: 7785260 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.1702. Min Act: -0.1700
Data Index: 1662857 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8577. Min Range: -7.8577
Max Act: 7.1389. Min Act: -0.1700
Data Index: 3605765 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19