Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1123 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0451. Min Range: -5.0451
Max Act: 5.0451. Min Act: -0.1700
Data Index: 6412211 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.9513. Min Act: -0.1700
Data Index: 5295770 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.8888. Min Act: -0.1700
Data Index: 7143500 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.8576. Min Act: -0.1700
Data Index: 2410174 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.8888. Min Act: -0.1700
Data Index: 3706202 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.8576. Min Act: -0.1700
Data Index: 1530785 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7638. Min Act: -0.1700
Data Index: 1972511 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7638. Min Act: -0.1700
Data Index: 2737718 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7326. Min Act: -0.1700
Data Index: 1595741 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7326. Min Act: -0.1700
Data Index: 2948491 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7638. Min Act: -0.1700
Data Index: 2129820 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7326. Min Act: -0.1700
Data Index: 3550879 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7013. Min Act: -0.1700
Data Index: 8408084 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7013. Min Act: -0.1700
Data Index: 1337271 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7013. Min Act: -0.1700
Data Index: 1533082 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7013. Min Act: -0.1700
Data Index: 4769000 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.7326. Min Act: -0.1700
Data Index: 3984106 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.6701. Min Act: -0.1700
Data Index: 8273123 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.6701. Min Act: -0.1700
Data Index: 2823793 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0451. Min Range: -5.0451
Max Act: 4.6701. Min Act: -0.1700
Data Index: 2501593 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19