Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2850. Min Range: -6.2850
Max Act: 6.2850. Min Act: -0.1700
Data Index: 2915802 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.8788. Min Act: -0.1700
Data Index: 8766365 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.7850. Min Act: -0.1700
Data Index: 329577 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.7538. Min Act: -0.1700
Data Index: 3417569 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.7850. Min Act: -0.1700
Data Index: 7323796 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.6600. Min Act: -0.1700
Data Index: 1131159 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.6288. Min Act: -0.1700
Data Index: 8580468 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5975. Min Act: -0.1700
Data Index: 2273853 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5975. Min Act: -0.1700
Data Index: 1863084 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5975. Min Act: -0.1700
Data Index: 220864 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5975. Min Act: -0.1700
Data Index: 6328861 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5663. Min Act: -0.1700
Data Index: 2448555 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5975. Min Act: -0.1700
Data Index: 7766646 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5663. Min Act: -0.1700
Data Index: 8156856 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4912253 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5663. Min Act: -0.1700
Data Index: 867551 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5663. Min Act: -0.1700
Data Index: 7219206 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5350. Min Act: -0.1700
Data Index: 7083990 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4024842 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2850. Min Range: -6.2850
Max Act: 5.5350. Min Act: -0.1700
Data Index: 2939904 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19