Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.5560. Min Act: -0.1700
Data Index: 5049741 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.5248. Min Act: -0.1700
Data Index: 2081833 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.4623. Min Act: -0.1700
Data Index: 3066369 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.4310. Min Act: -0.1700
Data Index: 7356890 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.3685. Min Act: -0.1700
Data Index: 4035045 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.3685. Min Act: -0.1700
Data Index: 8013825 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.3373. Min Act: -0.1700
Data Index: 2357532 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2748. Min Act: -0.1700
Data Index: 3874705 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2748. Min Act: -0.1700
Data Index: 5558135 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2748. Min Act: -0.1700
Data Index: 6288024 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2435. Min Act: -0.1700
Data Index: 7839427 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2748. Min Act: -0.1700
Data Index: 8370152 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2435. Min Act: -0.1700
Data Index: 6010037 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2435. Min Act: -0.1700
Data Index: 970669 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2435. Min Act: -0.1700
Data Index: 5739987 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2123. Min Act: -0.1700
Data Index: 676408 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2123. Min Act: -0.1700
Data Index: 3646108 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2435. Min Act: -0.1700
Data Index: 8241564 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.2123. Min Act: -0.1700
Data Index: 2176135 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5560. Min Range: -7.5560
Max Act: 7.1810. Min Act: -0.1700
Data Index: 5035391 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19