Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.4884. Min Act: -0.1700
Data Index: 2218849 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.4259. Min Act: -0.1700
Data Index: 2218850 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.2696. Min Act: -0.1700
Data Index: 2218848 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.2071. Min Act: -0.1700
Data Index: 3317329 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.0821. Min Act: -0.1700
Data Index: 7032959 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.0821. Min Act: -0.1700
Data Index: 2904925 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.0821. Min Act: -0.1700
Data Index: 2904926 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.0509. Min Act: -0.1700
Data Index: 4327829 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4884. Min Range: -5.4884
Max Act: 5.0196. Min Act: -0.1700
Data Index: 1612824 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9884. Min Act: -0.1700
Data Index: 506496 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9884. Min Act: -0.1700
Data Index: 3434190 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9884. Min Act: -0.1700
Data Index: 4519101 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9884. Min Act: -0.1700
Data Index: 8446207 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9884. Min Act: -0.1700
Data Index: 1570841 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9571. Min Act: -0.1700
Data Index: 2718704 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9259. Min Act: -0.1700
Data Index: 12202 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6430482 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9259. Min Act: -0.1700
Data Index: 2218853 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.9259. Min Act: -0.1700
Data Index: 8427118 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4884. Min Range: -5.4884
Max Act: 4.8946. Min Act: -0.1700
Data Index: 1612813 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19