Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.4778. Min Act: -0.1700
Data Index: 6612117 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.4466. Min Act: -0.1700
Data Index: 6360740 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.4466. Min Act: -0.1700
Data Index: 8484862 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.4466. Min Act: -0.1700
Data Index: 5434031 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.2591. Min Act: -0.1700
Data Index: 2264951 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.2278. Min Act: -0.1700
Data Index: 5906850 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1966. Min Act: -0.1700
Data Index: 2731408 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1966. Min Act: -0.1700
Data Index: 3158810 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1966. Min Act: -0.1700
Data Index: 900936 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1653. Min Act: -0.1700
Data Index: 8257215 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1653. Min Act: -0.1700
Data Index: 7122752 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1653. Min Act: -0.1700
Data Index: 4599563 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1341. Min Act: -0.1700
Data Index: 3560459 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.0716. Min Act: -0.1697
Data Index: 4599574 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1028. Min Act: -0.1700
Data Index: 4970912 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1028. Min Act: -0.1700
Data Index: 5443586 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1341. Min Act: -0.1700
Data Index: 5434038 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.1028. Min Act: -0.1699
Data Index: 1495207 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.0716. Min Act: -0.1696
Data Index: 8653806 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4778. Min Range: -6.4778
Max Act: 6.0403. Min Act: -0.1700
Data Index: 5219336 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19