Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2862. Min Range: -11.2862
Max Act: 11.2862. Min Act: -0.1700
Data Index: 4733814 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2862. Min Range: -11.2862
Max Act: 11.0987. Min Act: -0.1700
Data Index: 4367820 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2862. Min Range: -11.2862
Max Act: 11.0362. Min Act: -0.1700
Data Index: 3806326 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.9737. Min Act: -0.1700
Data Index: 1124750 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.9112. Min Act: -0.1700
Data Index: 6839932 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.8487. Min Act: -0.1700
Data Index: 7834857 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.7237. Min Act: -0.1700
Data Index: 1828570 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.6612. Min Act: -0.1700
Data Index: 6901399 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.7237. Min Act: -0.1700
Data Index: 870983 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.5362. Min Act: -0.1700
Data Index: 397706 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.4737. Min Act: -0.1700
Data Index: 3300182 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.5362. Min Act: -0.1700
Data Index: 7847747 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.4112. Min Act: -0.1700
Data Index: 6043217 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.3487. Min Act: -0.1700
Data Index: 2984134 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.4112. Min Act: -0.1700
Data Index: 431190 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.3487. Min Act: -0.1700
Data Index: 3756482 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.3487. Min Act: -0.1700
Data Index: 4351344 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.2862. Min Act: -0.1700
Data Index: 3853674 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.2862. Min Act: -0.1700
Data Index: 1998831 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2862. Min Range: -11.2862
Max Act: 10.2862. Min Act: -0.1700
Data Index: 3272358 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19