Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0980. Min Range: -6.0980
Max Act: 6.0980. Min Act: -0.1700
Data Index: 1755270 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.9417. Min Act: -0.1700
Data Index: 2395995 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.9105. Min Act: -0.1700
Data Index: 1595930 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.9105. Min Act: -0.1700
Data Index: 5617781 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.9417. Min Act: -0.1700
Data Index: 6457731 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.8480. Min Act: -0.1700
Data Index: 8770245 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.8480. Min Act: -0.1700
Data Index: 3111181 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.8167. Min Act: -0.1700
Data Index: 1645014 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.7855. Min Act: -0.1700
Data Index: 1396622 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.6917. Min Act: -0.1700
Data Index: 4046524 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.6605. Min Act: -0.1700
Data Index: 958051 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.6605. Min Act: -0.1700
Data Index: 3880795 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.6292. Min Act: -0.1700
Data Index: 8596059 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.5980. Min Act: -0.1700
Data Index: 4814820 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5351009 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.5667. Min Act: -0.1700
Data Index: 2879748 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5294582 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.5980. Min Act: -0.1700
Data Index: 5553746 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.5355. Min Act: -0.1700
Data Index: 325974 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0980. Min Range: -6.0980
Max Act: 5.4730. Min Act: -0.1700
Data Index: 3693102 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19