Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.7399. Min Act: -0.1700
Data Index: 5057224 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.5211. Min Act: -0.1700
Data Index: 1767024 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.5211. Min Act: -0.1700
Data Index: 7567270 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.3336. Min Act: -0.1700
Data Index: 4200605 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.2399. Min Act: -0.1700
Data Index: 8612042 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.2399. Min Act: -0.1700
Data Index: 3326852 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.2399. Min Act: -0.1700
Data Index: 3697506 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.2086. Min Act: -0.1700
Data Index: 8289910 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.2086. Min Act: -0.1700
Data Index: 4068523 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.2086. Min Act: -0.1700
Data Index: 7581862 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.1461. Min Act: -0.1700
Data Index: 7471834 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.1461. Min Act: -0.1700
Data Index: 4746448 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 2365750 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.0836. Min Act: -0.1700
Data Index: 7145818 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.1149. Min Act: -0.1700
Data Index: 3903213 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.0836. Min Act: -0.1700
Data Index: 1153884 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.0524. Min Act: -0.1700
Data Index: 2344184 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.0524. Min Act: -0.1700
Data Index: 3585236 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.0524. Min Act: -0.1700
Data Index: 3510917 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7399. Min Range: -6.7399
Max Act: 6.0211. Min Act: -0.1700
Data Index: 5892871 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19