Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.7884. Min Act: -0.1700
Data Index: 8617637 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.6009. Min Act: -0.1700
Data Index: 1173283 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.5072. Min Act: -0.1700
Data Index: 8445031 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.4759. Min Act: -0.1700
Data Index: 1455424 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.4134. Min Act: -0.1700
Data Index: 2197279 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.4134. Min Act: -0.1700
Data Index: 5033772 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.4447. Min Act: -0.1700
Data Index: 7710145 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.4447. Min Act: -0.1700
Data Index: 6142817 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.4134. Min Act: -0.1700
Data Index: 2966150 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.3822. Min Act: -0.1700
Data Index: 783521 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.3822. Min Act: -0.1700
Data Index: 5296660 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.3509. Min Act: -0.1700
Data Index: 4046983 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.3197. Min Act: -0.1700
Data Index: 716776 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2884. Min Act: -0.1700
Data Index: 6178166 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2884. Min Act: -0.1700
Data Index: 48926 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2884. Min Act: -0.1700
Data Index: 123836 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2572. Min Act: -0.1700
Data Index: 4545726 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2572. Min Act: -0.1700
Data Index: 3264715 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2572. Min Act: -0.1700
Data Index: 954742 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7884. Min Range: -4.7884
Max Act: 4.2884. Min Act: -0.1700
Data Index: 3594654 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19