Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.3905. Min Act: -0.1700
Data Index: 8603182 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.3280. Min Act: -0.1700
Data Index: 8569316 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.3280. Min Act: -0.1700
Data Index: 2826904 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2968. Min Act: -0.1700
Data Index: 4996486 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2655. Min Act: -0.1700
Data Index: 8603186 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2655. Min Act: -0.1700
Data Index: 4064973 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2343. Min Act: -0.1700
Data Index: 8270990 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2030. Min Act: -0.1700
Data Index: 7094647 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2030. Min Act: -0.1700
Data Index: 2745563 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2030. Min Act: -0.1700
Data Index: 1207713 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1718. Min Act: -0.1700
Data Index: 153295 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1718. Min Act: -0.1700
Data Index: 660020 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1405. Min Act: -0.1700
Data Index: 8789093 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1093. Min Act: -0.1700
Data Index: 4121837 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1093. Min Act: -0.1699
Data Index: 5853061 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1093. Min Act: -0.1700
Data Index: 3311917 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0780. Min Act: -0.1700
Data Index: 198122 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0780. Min Act: -0.1700
Data Index: 1884037 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0780. Min Act: -0.1700
Data Index: 315548 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0780. Min Act: -0.1700
Data Index: 1284996 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19