Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.2214. Min Act: -0.1700
Data Index: 248246 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.2057. Min Act: -0.1700
Data Index: 7392281 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.1585. Min Act: -0.1700
Data Index: 5181814 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0482. Min Act: -0.1700
Data Index: 1022753 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0008. Min Act: -0.1700
Data Index: 8708850 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9534. Min Act: -0.1700
Data Index: 4943585 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9376. Min Act: -0.1700
Data Index: 5065356 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9376. Min Act: -0.1700
Data Index: 837674 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9376. Min Act: -0.1700
Data Index: 2490209 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9217. Min Act: -0.1700
Data Index: 1819939 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9534. Min Act: -0.1700
Data Index: 6652974 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9217. Min Act: -0.1700
Data Index: 8441942 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9059. Min Act: -0.1700
Data Index: 8102870 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9217. Min Act: -0.1700
Data Index: 4456955 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.8900. Min Act: -0.1700
Data Index: 8159324 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.8900. Min Act: -0.1700
Data Index: 5222960 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.8741. Min Act: -0.1700
Data Index: 7321247 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.8583. Min Act: -0.1700
Data Index: 173900 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.8741. Min Act: -0.1700
Data Index: 5236447 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.8583. Min Act: -0.1700
Data Index: 7249926 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19