Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.6854. Min Act: -0.1700
Data Index: 6604042 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.6229. Min Act: -0.1700
Data Index: 5765115 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.5604. Min Act: -0.1700
Data Index: 7458280 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.5604. Min Act: -0.1700
Data Index: 3135637 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.5291. Min Act: -0.1700
Data Index: 4781474 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4979. Min Act: -0.1700
Data Index: 3939548 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.5291. Min Act: -0.1700
Data Index: 1752052 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.5291. Min Act: -0.1700
Data Index: 5623366 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4666. Min Act: -0.1700
Data Index: 8651384 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4979. Min Act: -0.1700
Data Index: 8764383 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4666. Min Act: -0.1700
Data Index: 4128946 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4354. Min Act: -0.1700
Data Index: 6354861 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4666. Min Act: -0.1700
Data Index: 4091400 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4354. Min Act: -0.1700
Data Index: 2290620 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4354. Min Act: -0.1700
Data Index: 4102449 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4041. Min Act: -0.1700
Data Index: 4694745 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.3729. Min Act: -0.1700
Data Index: 2132082 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.3416. Min Act: -0.1700
Data Index: 7151571 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.3729. Min Act: -0.1700
Data Index: 2253449 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6854. Min Range: -5.6854
Max Act: 5.4041. Min Act: -0.1700
Data Index: 3083465 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19