Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4135 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.9499. Min Act: -0.1700
Data Index: 7149918 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.8249. Min Act: -0.1700
Data Index: 4463217 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.7936. Min Act: -0.1700
Data Index: 3271246 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.8249. Min Act: -0.1700
Data Index: 5010797 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.7624. Min Act: -0.1700
Data Index: 5130928 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.7311. Min Act: -0.1700
Data Index: 4463216 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.7311. Min Act: -0.1700
Data Index: 448991 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.7311. Min Act: -0.1700
Data Index: 6839744 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.7311. Min Act: -0.1700
Data Index: 6268146 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6999. Min Act: -0.1700
Data Index: 8471552 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6686. Min Act: -0.1700
Data Index: 5582957 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6999. Min Act: -0.1700
Data Index: 1333174 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6374. Min Act: -0.1700
Data Index: 6638381 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6061. Min Act: -0.1700
Data Index: 5202619 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6061. Min Act: -0.1700
Data Index: 4820611 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.6061. Min Act: -0.1700
Data Index: 1398601 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.5749. Min Act: -0.1700
Data Index: 5047384 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.5749. Min Act: -0.1700
Data Index: 2839837 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.5436. Min Act: -0.1700
Data Index: 640403 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9499. Min Range: -4.9499
Max Act: 4.5436. Min Act: -0.1700
Data Index: 640400 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19