Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1022 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.8328. Min Act: -0.1700
Data Index: 4645718 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.8169. Min Act: -0.1700
Data Index: 7375491 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7372. Min Act: -0.1700
Data Index: 2404568 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7212. Min Act: -0.1700
Data Index: 1461186 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7212. Min Act: -0.1700
Data Index: 8194026 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7052. Min Act: -0.1700
Data Index: 4260768 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.7052. Min Act: -0.1700
Data Index: 6132590 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6892. Min Act: -0.1700
Data Index: 5149608 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6411. Min Act: -0.1700
Data Index: 2783184 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6571. Min Act: -0.1700
Data Index: 6537454 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6250. Min Act: -0.1700
Data Index: 7042160 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6411. Min Act: -0.1700
Data Index: 6747230 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6089. Min Act: -0.1700
Data Index: 7228340 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6571. Min Act: -0.1700
Data Index: 8279877 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6089. Min Act: -0.1700
Data Index: 1450364 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.5928. Min Act: -0.1700
Data Index: 8446350 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6250. Min Act: -0.1700
Data Index: 8784110 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6250. Min Act: -0.1700
Data Index: 3597045 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6089. Min Act: -0.1700
Data Index: 6043204 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8328. Min Range: -2.8328
Max Act: 2.6089. Min Act: -0.1700
Data Index: 1847099 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19