Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 581 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.1631. Min Act: -0.1700
Data Index: 6048860 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.1319. Min Act: -0.1700
Data Index: 2197988 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.0381. Min Act: -0.1700
Data Index: 3863518 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.0694. Min Act: -0.1700
Data Index: 6745784 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.0694. Min Act: -0.1700
Data Index: 4700921 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.0381. Min Act: -0.1700
Data Index: 2465301 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.0069. Min Act: -0.1700
Data Index: 6663336 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1631. Min Range: -4.1631
Max Act: 4.0069. Min Act: -0.1700
Data Index: 3100116 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9756. Min Act: -0.1700
Data Index: 7805220 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9756. Min Act: -0.1700
Data Index: 7725214 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9443. Min Act: -0.1700
Data Index: 6280598 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9443. Min Act: -0.1700
Data Index: 694227 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9443. Min Act: -0.1700
Data Index: 1475657 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9443. Min Act: -0.1700
Data Index: 3100118 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9443. Min Act: -0.1700
Data Index: 2080981 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9131. Min Act: -0.1700
Data Index: 2197989 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.8818. Min Act: -0.1700
Data Index: 4512212 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9131. Min Act: -0.1700
Data Index: 1421301 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9131. Min Act: -0.1700
Data Index: 2642133 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1631. Min Range: -4.1631
Max Act: 3.9131. Min Act: -0.1700
Data Index: 7659288 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19