Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.3692. Min Act: -0.1700
Data Index: 1617178 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.1504. Min Act: -0.1700
Data Index: 7169459 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.1504. Min Act: -0.1700
Data Index: 1186626 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.0879. Min Act: -0.1700
Data Index: 7541530 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.0567. Min Act: -0.1700
Data Index: 3254034 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.0254. Min Act: -0.1700
Data Index: 4595454 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3692. Min Range: -5.3692
Max Act: 5.0254. Min Act: -0.1700
Data Index: 5962490 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9942. Min Act: -0.1700
Data Index: 7071665 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9942. Min Act: -0.1700
Data Index: 4455738 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9942. Min Act: -0.1700
Data Index: 2880049 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9942. Min Act: -0.1700
Data Index: 1480701 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9629. Min Act: -0.1700
Data Index: 2467074 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9317. Min Act: -0.1700
Data Index: 2524927 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9629. Min Act: -0.1700
Data Index: 8677429 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9004. Min Act: -0.1700
Data Index: 7335261 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9004. Min Act: -0.1700
Data Index: 8396584 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.8692. Min Act: -0.1700
Data Index: 4204019 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.8692. Min Act: -0.1700
Data Index: 7062753 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.8692. Min Act: -0.1700
Data Index: 4102230 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3692. Min Range: -5.3692
Max Act: 4.9004. Min Act: -0.1700
Data Index: 6166067 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19