Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1478. Min Range: -5.1478
Max Act: 5.1478. Min Act: -0.1700
Data Index: 3748224 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1478. Min Range: -5.1478
Max Act: 5.1166. Min Act: -0.1700
Data Index: 5850881 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1478. Min Range: -5.1478
Max Act: 5.0228. Min Act: -0.1700
Data Index: 7049045 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.9603. Min Act: -0.1700
Data Index: 6830906 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.8978. Min Act: -0.1700
Data Index: 3632792 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.8041. Min Act: -0.1700
Data Index: 6117309 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.8666. Min Act: -0.1700
Data Index: 4443970 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.8041. Min Act: -0.1700
Data Index: 7480520 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7728. Min Act: -0.1700
Data Index: 4382218 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7728. Min Act: -0.1700
Data Index: 8622603 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7416. Min Act: -0.1700
Data Index: 4221147 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7103. Min Act: -0.1700
Data Index: 7345870 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7103. Min Act: -0.1700
Data Index: 1603653 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7103. Min Act: -0.1700
Data Index: 6880541 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7416. Min Act: -0.1700
Data Index: 7992172 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.6791. Min Act: -0.1700
Data Index: 3227762 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.7416. Min Act: -0.1700
Data Index: 3087647 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.6478. Min Act: -0.1700
Data Index: 8342395 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.6791. Min Act: -0.1700
Data Index: 6436282 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1478. Min Range: -5.1478
Max Act: 4.6791. Min Act: -0.1700
Data Index: 7711085 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19