Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0614. Min Range: -7.0614
Max Act: 7.0614. Min Act: -0.1700
Data Index: 4485347 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9364. Min Act: -0.1700
Data Index: 8185544 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9989. Min Act: -0.1700
Data Index: 4126176 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9677. Min Act: -0.1700
Data Index: 4632709 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9677. Min Act: -0.1700
Data Index: 2835774 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9364. Min Act: -0.1700
Data Index: 798206 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9052. Min Act: -0.1700
Data Index: 6161427 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9052. Min Act: -0.1700
Data Index: 1820192 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 2392712 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 4087154 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 603006 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 497078 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 1806416 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 227872 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9052. Min Act: -0.1700
Data Index: 4835167 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 1034259 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 7503542 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 6285886 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.9052. Min Act: -0.1700
Data Index: 5114163 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0614. Min Range: -7.0614
Max Act: 6.8739. Min Act: -0.1700
Data Index: 7579056 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19