Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.9486. Min Act: -0.1700
Data Index: 3252646 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.7299. Min Act: -0.1700
Data Index: 1576984 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.6986. Min Act: -0.1700
Data Index: 5647478 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.6361. Min Act: -0.1700
Data Index: 4864903 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.6049. Min Act: -0.1700
Data Index: 2119716 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.5736. Min Act: -0.1700
Data Index: 6795933 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.5424. Min Act: -0.1700
Data Index: 639996 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.5424. Min Act: -0.1700
Data Index: 6795938 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.5111. Min Act: -0.1700
Data Index: 7521386 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.5111. Min Act: -0.1700
Data Index: 334562 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.5111. Min Act: -0.1700
Data Index: 3899719 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4799. Min Act: -0.1700
Data Index: 1238037 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4799. Min Act: -0.1700
Data Index: 1091428 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4486. Min Act: -0.1700
Data Index: 1195751 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4799. Min Act: -0.1700
Data Index: 5195688 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4174. Min Act: -0.1700
Data Index: 7835402 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4174. Min Act: -0.1700
Data Index: 2624777 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.4174. Min Act: -0.1700
Data Index: 5520587 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.3549. Min Act: -0.1700
Data Index: 2364987 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9486. Min Range: -5.9486
Max Act: 5.3549. Min Act: -0.1700
Data Index: 5467965 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19