Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5766 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.6338. Min Act: -0.1700
Data Index: 7247375 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.4150. Min Act: -0.1700
Data Index: 2551045 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3838. Min Act: -0.1700
Data Index: 6434892 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3838. Min Act: -0.1700
Data Index: 7013354 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 4282051 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2275. Min Act: -0.1700
Data Index: 7083053 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2275. Min Act: -0.1700
Data Index: 5770688 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1963. Min Act: -0.1700
Data Index: 5765669 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1963. Min Act: -0.1700
Data Index: 478519 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1650. Min Act: -0.1700
Data Index: 2271932 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1650. Min Act: -0.1700
Data Index: 4345494 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1338. Min Act: -0.1700
Data Index: 4685628 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1338. Min Act: -0.1700
Data Index: 1410810 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1025. Min Act: -0.1700
Data Index: 8520660 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.1025. Min Act: -0.1700
Data Index: 4526729 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.0713. Min Act: -0.1700
Data Index: 8225709 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.0713. Min Act: -0.1700
Data Index: 7389502 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.0713. Min Act: -0.1700
Data Index: 5989920 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.0400. Min Act: -0.1700
Data Index: 2099520 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.0088. Min Act: -0.1700
Data Index: 319187 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19