Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1707. Min Act: -0.1700
Data Index: 5675488 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.2019. Min Act: -0.1700
Data Index: 7014154 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0769. Min Act: -0.1700
Data Index: 5073376 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0144. Min Act: -0.1700
Data Index: 4900056 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9832. Min Act: -0.1700
Data Index: 6317388 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9832. Min Act: -0.1700
Data Index: 1372196 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9519. Min Act: -0.1700
Data Index: 8234010 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9519. Min Act: -0.1700
Data Index: 5554282 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 4347047 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 1440772 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 7125981 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 2463191 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8894. Min Act: -0.1700
Data Index: 4324743 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8582. Min Act: -0.1700
Data Index: 809906 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8582. Min Act: -0.1700
Data Index: 7793320 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8582. Min Act: -0.1700
Data Index: 1995251 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8269. Min Act: -0.1700
Data Index: 4434176 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8269. Min Act: -0.1700
Data Index: 38953 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8269. Min Act: -0.1700
Data Index: 2318367 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8269. Min Act: -0.1700
Data Index: 3926003 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19