Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.4811. Min Act: -0.1700
Data Index: 4065188 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.4498. Min Act: -0.1700
Data Index: 8685198 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.2936. Min Act: -0.1700
Data Index: 4102752 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.2311. Min Act: -0.1700
Data Index: 2037627 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.2311. Min Act: -0.1700
Data Index: 5678473 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.1686. Min Act: -0.1700
Data Index: 1433046 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.1061. Min Act: -0.1700
Data Index: 3620472 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.1061. Min Act: -0.1700
Data Index: 4770643 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.0123. Min Act: -0.1700
Data Index: 1044734 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.0436. Min Act: -0.1700
Data Index: 4102967 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4811. Min Range: -7.4811
Max Act: 7.0123. Min Act: -0.1700
Data Index: 6470944 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.9811. Min Act: -0.1700
Data Index: 2644361 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.9186. Min Act: -0.1700
Data Index: 795441 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.9186. Min Act: -0.1700
Data Index: 7565843 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.9186. Min Act: -0.1700
Data Index: 184509 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.8561. Min Act: -0.1700
Data Index: 2751825 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.8873. Min Act: -0.1700
Data Index: 4309535 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.8561. Min Act: -0.1700
Data Index: 6942441 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.8561. Min Act: -0.1700
Data Index: 1212194 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4811. Min Range: -7.4811
Max Act: 6.8248. Min Act: -0.1700
Data Index: 2862848 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19