Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2413 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1461. Min Range: -4.1461
Max Act: 4.1461. Min Act: -0.1700
Data Index: 511294 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.9742. Min Act: -0.1700
Data Index: 7941302 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.9117. Min Act: -0.1700
Data Index: 6894597 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.9273. Min Act: -0.1700
Data Index: 4552237 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8960. Min Act: -0.1700
Data Index: 1124961 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8960. Min Act: -0.1700
Data Index: 1627639 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8491. Min Act: -0.1700
Data Index: 8537927 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8491. Min Act: -0.1700
Data Index: 3984070 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8648. Min Act: -0.1700
Data Index: 2592016 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8335. Min Act: -0.1700
Data Index: 5210625 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8022. Min Act: -0.1700
Data Index: 889857 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8335. Min Act: -0.1700
Data Index: 1835734 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8179. Min Act: -0.1700
Data Index: 6116154 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.8022. Min Act: -0.1700
Data Index: 2744388 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.7553. Min Act: -0.1700
Data Index: 6636491 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.7866. Min Act: -0.1700
Data Index: 2990684 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.7866. Min Act: -0.1700
Data Index: 2667249 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.7709. Min Act: -0.1700
Data Index: 6862580 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.7866. Min Act: -0.1700
Data Index: 4254827 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1461. Min Range: -4.1461
Max Act: 3.7709. Min Act: -0.1700
Data Index: 1500529 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19