Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.6912. Min Act: -0.1700
Data Index: 8790868 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5975. Min Act: -0.1700
Data Index: 7536585 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5662. Min Act: -0.1699
Data Index: 4813758 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5662. Min Act: -0.1700
Data Index: 6493263 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 5262056 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 6311750 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 8807937 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5662. Min Act: -0.1700
Data Index: 8151626 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 5926971 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 5851897 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 2537216 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4663686 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1694
Data Index: 3492393 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 6401530 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 2254832 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 1897799 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4862294 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 7513890 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4670243 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6912. Min Range: -5.6912
Max Act: 5.5037. Min Act: -0.1700
Data Index: 4414813 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19