Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2513. Min Range: -4.2513
Max Act: 4.2513. Min Act: -0.1700
Data Index: 1958275 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.9387. Min Act: -0.1700
Data Index: 1422285 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.9075. Min Act: -0.1700
Data Index: 8464534 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.8918. Min Act: -0.1700
Data Index: 4087688 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.8762. Min Act: -0.1700
Data Index: 5794764 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.8449. Min Act: -0.1700
Data Index: 2821725 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.8293. Min Act: -0.1700
Data Index: 7388180 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.8137. Min Act: -0.1700
Data Index: 8706670 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.8293. Min Act: -0.1700
Data Index: 4037617 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7980. Min Act: -0.1700
Data Index: 1962087 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7824. Min Act: -0.1700
Data Index: 6405693 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7980. Min Act: -0.1700
Data Index: 6796198 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7824. Min Act: -0.1700
Data Index: 1725384 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7667. Min Act: -0.1700
Data Index: 3956727 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7667. Min Act: -0.1700
Data Index: 6701086 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7355. Min Act: -0.1700
Data Index: 3640114 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7667. Min Act: -0.1700
Data Index: 1896879 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7355. Min Act: -0.1700
Data Index: 2674610 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7198. Min Act: -0.1700
Data Index: 3638420 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2513. Min Range: -4.2513
Max Act: 3.7198. Min Act: -0.1700
Data Index: 1273129 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19