Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.9622. Min Act: -0.1700
Data Index: 2348689 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.5560. Min Act: -0.1700
Data Index: 2160450 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.5872. Min Act: -0.1700
Data Index: 2792762 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.4622. Min Act: -0.1700
Data Index: 2832444 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.3685. Min Act: -0.1700
Data Index: 8018605 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.3372. Min Act: -0.1700
Data Index: 6986890 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.3372. Min Act: -0.1700
Data Index: 4490720 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.3060. Min Act: -0.1700
Data Index: 2106056 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.2747. Min Act: -0.1700
Data Index: 3351577 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.2435. Min Act: -0.1700
Data Index: 5364312 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1675770 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1810. Min Act: -0.1700
Data Index: 6654911 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1810. Min Act: -0.1700
Data Index: 6890254 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1810. Min Act: -0.1700
Data Index: 2063813 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1162181 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1185. Min Act: -0.1700
Data Index: 5308186 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1497. Min Act: -0.1700
Data Index: 328513 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1497. Min Act: -0.1700
Data Index: 167472 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1497. Min Act: -0.1700
Data Index: 543189 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9622. Min Range: -6.9622
Max Act: 6.1185. Min Act: -0.1700
Data Index: 5861395 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19