Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.5457. Min Act: -0.1700
Data Index: 1549306 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7038639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.4207. Min Act: -0.1700
Data Index: 5540413 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 1394153 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 785334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 4898420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 6366018 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 3752263 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 1023639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 4110466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1242950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.3269. Min Act: -0.1700
Data Index: 3930240 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1553977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 6699464 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 421039 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 7038644 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2332. Min Act: -0.1700
Data Index: 2555437 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 7531879 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 5235241 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5457. Min Range: -5.5457
Max Act: 5.2644. Min Act: -0.1700
Data Index: 3900316 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19