Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 544 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.2547. Min Act: -0.1700
Data Index: 884 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0816. Min Act: -0.1700
Data Index: 5100900 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0501. Min Act: -0.1700
Data Index: 2188236 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0343. Min Act: -0.1700
Data Index: 6296139 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0658. Min Act: -0.1700
Data Index: 6218817 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0501. Min Act: -0.1700
Data Index: 7168714 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0185. Min Act: -0.1700
Data Index: 8789691 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2547. Min Range: -3.2547
Max Act: 3.0185. Min Act: -0.1700
Data Index: 1068069 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9869. Min Act: -0.1700
Data Index: 6168724 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9711. Min Act: -0.1700
Data Index: 5046485 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9711. Min Act: -0.1700
Data Index: 1612147 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9711. Min Act: -0.1700
Data Index: 5673809 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9553. Min Act: -0.1700
Data Index: 3128764 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9869. Min Act: -0.1700
Data Index: 5790592 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9869. Min Act: -0.1700
Data Index: 3865853 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9869. Min Act: -0.1700
Data Index: 4324826 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9394. Min Act: -0.1700
Data Index: 131567 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9394. Min Act: -0.1700
Data Index: 3377645 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9394. Min Act: -0.1700
Data Index: 3363847 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2547. Min Range: -3.2547
Max Act: 2.9236. Min Act: -0.1700
Data Index: 486231 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19