Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2868. Min Range: -4.2868
Max Act: 4.2868. Min Act: -0.1699
Data Index: 4568820 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2868. Min Range: -4.2868
Max Act: 4.2243. Min Act: -0.1700
Data Index: 4132485 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2868. Min Range: -4.2868
Max Act: 4.1930. Min Act: -0.1700
Data Index: 3167659 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2868. Min Range: -4.2868
Max Act: 4.0680. Min Act: -0.1700
Data Index: 4132486 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.9742. Min Act: -0.1700
Data Index: 594178 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.9742. Min Act: -0.1700
Data Index: 4132483 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.9429. Min Act: -0.1700
Data Index: 2299313 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.9429. Min Act: -0.1700
Data Index: 5908463 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.9117. Min Act: -0.1700
Data Index: 6919283 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8804. Min Act: -0.1700
Data Index: 3794065 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8491. Min Act: -0.1700
Data Index: 3362238 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8491. Min Act: -0.1700
Data Index: 482066 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8491. Min Act: -0.1700
Data Index: 7679827 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8491. Min Act: -0.1700
Data Index: 560523 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8491. Min Act: -0.1700
Data Index: 4132489 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8179. Min Act: -0.1700
Data Index: 1148406 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8179. Min Act: -0.1700
Data Index: 2913616 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.8491. Min Act: -0.1700
Data Index: 1377148 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.7866. Min Act: -0.1700
Data Index: 4132497 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2868. Min Range: -4.2868
Max Act: 3.7866. Min Act: -0.1700
Data Index: 4158066 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19