Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0422. Min Range: -3.0422
Max Act: 3.0422. Min Act: -0.1700
Data Index: 4545695 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9948. Min Act: -0.1700
Data Index: 3929176 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0422. Min Range: -3.0422
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5834137 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9790. Min Act: -0.1700
Data Index: 7905745 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9473. Min Act: -0.1700
Data Index: 3595277 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9315. Min Act: -0.1700
Data Index: 7152563 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9473. Min Act: -0.1700
Data Index: 3647123 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9315. Min Act: -0.1700
Data Index: 2846129 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9473. Min Act: -0.1700
Data Index: 7689175 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8998. Min Act: -0.1700
Data Index: 134433 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9156. Min Act: -0.1700
Data Index: 1889449 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8998. Min Act: -0.1700
Data Index: 3106505 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8998. Min Act: -0.1700
Data Index: 746140 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9156. Min Act: -0.1700
Data Index: 6263735 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8998. Min Act: -0.1695
Data Index: 4944625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.9156. Min Act: -0.1700
Data Index: 7003673 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8680. Min Act: -0.1700
Data Index: 5582563 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8839. Min Act: -0.1700
Data Index: 2391628 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8680. Min Act: -0.1700
Data Index: 4369456 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0422. Min Range: -3.0422
Max Act: 2.8680. Min Act: -0.1700
Data Index: 6737508 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19