Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2439 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.9672. Min Act: -0.1698
Data Index: 3917405 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.9333. Min Act: -0.1647
Data Index: 6562419 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.9162. Min Act: -0.1700
Data Index: 1796176 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.9162. Min Act: -0.1697
Data Index: 752636 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8992. Min Act: -0.1700
Data Index: 5303640 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8992. Min Act: -0.1698
Data Index: 8013893 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8821. Min Act: -0.1700
Data Index: 4161604 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8821. Min Act: -0.1700
Data Index: 5310210 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8821. Min Act: -0.1699
Data Index: 2432698 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8821. Min Act: -0.1700
Data Index: 1549517 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8821. Min Act: -0.1699
Data Index: 7852555 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1700
Data Index: 8681743 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1699
Data Index: 5630043 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1700
Data Index: 8263991 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1680
Data Index: 5336316 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1621
Data Index: 1492856 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1699
Data Index: 7448005 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8650. Min Act: -0.1700
Data Index: 7353305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8479. Min Act: -0.1665
Data Index: 1438802 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9672. Min Range: -1.9672
Max Act: 1.8479. Min Act: -0.1697
Data Index: 1416303 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19