Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2522. Min Range: -5.2522
Max Act: 5.2522. Min Act: -0.1700
Data Index: 218633 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2522. Min Range: -5.2522
Max Act: 5.0960. Min Act: -0.1700
Data Index: 2806325 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2522. Min Range: -5.2522
Max Act: 5.0960. Min Act: -0.1700
Data Index: 4469370 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2522. Min Range: -5.2522
Max Act: 5.0335. Min Act: -0.1700
Data Index: 8687105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2522. Min Range: -5.2522
Max Act: 5.0022. Min Act: -0.1700
Data Index: 618029 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.9397. Min Act: -0.1700
Data Index: 607424 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.9710. Min Act: -0.1700
Data Index: 6660021 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.9397. Min Act: -0.1700
Data Index: 2072898 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.9085. Min Act: -0.1700
Data Index: 130904 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.9397. Min Act: -0.1700
Data Index: 130903 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8772. Min Act: -0.1700
Data Index: 3184592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8772. Min Act: -0.1700
Data Index: 4277256 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8772. Min Act: -0.1700
Data Index: 5694274 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.9085. Min Act: -0.1700
Data Index: 7131653 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8460. Min Act: -0.1700
Data Index: 6625437 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8460. Min Act: -0.1700
Data Index: 2075020 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8460. Min Act: -0.1700
Data Index: 3231099 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8460. Min Act: -0.1700
Data Index: 3443158 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8460. Min Act: -0.1700
Data Index: 2199517 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2522. Min Range: -5.2522
Max Act: 4.8460. Min Act: -0.1700
Data Index: 3802165 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19