Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5826 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.4221. Min Act: -0.1700
Data Index: 2912852 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.4221. Min Act: -0.1700
Data Index: 8318204 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.3437. Min Act: -0.1700
Data Index: 506258 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.3280. Min Act: -0.1700
Data Index: 195501 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.3123. Min Act: -0.1700
Data Index: 5327733 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.2967. Min Act: -0.1700
Data Index: 3719234 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.2809. Min Act: -0.1700
Data Index: 2683652 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.2181. Min Act: -0.1700
Data Index: 3197204 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.2181. Min Act: -0.1700
Data Index: 5581115 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.2024. Min Act: -0.1700
Data Index: 1594420 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.2024. Min Act: -0.1700
Data Index: 3365029 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1867. Min Act: -0.1700
Data Index: 690547 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1867. Min Act: -0.1700
Data Index: 4664630 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1867. Min Act: -0.1700
Data Index: 2070725 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1867. Min Act: -0.1700
Data Index: 829899 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1709. Min Act: -0.1700
Data Index: 5738216 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1709. Min Act: -0.1700
Data Index: 7832936 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1552. Min Act: -0.1700
Data Index: 4144884 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1552. Min Act: -0.1700
Data Index: 2927225 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4221. Min Range: -3.4221
Max Act: 3.1552. Min Act: -0.1700
Data Index: 6777012 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19