Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4949 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1519. Min Range: -3.1519
Max Act: 3.1519. Min Act: -0.1698
Data Index: 6872287 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.9150. Min Act: -0.1700
Data Index: 7326432 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.8197. Min Act: -0.1699
Data Index: 5285047 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.8356. Min Act: -0.1700
Data Index: 1115205 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.8038. Min Act: -0.1700
Data Index: 5747014 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.7879. Min Act: -0.1700
Data Index: 4372163 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.7879. Min Act: -0.1700
Data Index: 7943228 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.7560. Min Act: -0.1699
Data Index: 5991173 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.7560. Min Act: -0.1700
Data Index: 121833 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.7400. Min Act: -0.1700
Data Index: 4115417 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.7081. Min Act: -0.1700
Data Index: 3176539 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6760. Min Act: -0.1700
Data Index: 1416729 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6760. Min Act: -0.1700
Data Index: 5965750 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6600. Min Act: -0.1700
Data Index: 2387670 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6600. Min Act: -0.1700
Data Index: 6071293 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6440. Min Act: -0.1700
Data Index: 8667633 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6440. Min Act: -0.1697
Data Index: 431687 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6440. Min Act: -0.1700
Data Index: 2128398 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6440. Min Act: -0.1700
Data Index: 4180810 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1519. Min Range: -3.1519
Max Act: 2.6440. Min Act: -0.1700
Data Index: 5071120 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19