Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0256. Min Range: -9.0256
Max Act: 9.0256. Min Act: -0.1700
Data Index: 5992312 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0256. Min Range: -9.0256
Max Act: 8.0256. Min Act: -0.1700
Data Index: 6184376 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0256. Min Range: -9.0256
Max Act: 8.0256. Min Act: -0.1700
Data Index: 1637150 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.9631. Min Act: -0.1700
Data Index: 4189416 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.9631. Min Act: -0.1700
Data Index: 523388 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.9006. Min Act: -0.1700
Data Index: 3820828 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.9006. Min Act: -0.1700
Data Index: 7135306 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.7756. Min Act: -0.1700
Data Index: 1788685 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.7756. Min Act: -0.1700
Data Index: 472448 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.7131. Min Act: -0.1700
Data Index: 2203780 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.6506. Min Act: -0.1700
Data Index: 7728657 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5881. Min Act: -0.1700
Data Index: 3965808 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.6506. Min Act: -0.1700
Data Index: 758170 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5881. Min Act: -0.1700
Data Index: 6566124 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5881. Min Act: -0.1700
Data Index: 3709104 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5256. Min Act: -0.1700
Data Index: 5116841 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5881. Min Act: -0.1700
Data Index: 5063184 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5881. Min Act: -0.1700
Data Index: 4149087 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5881. Min Act: -0.1700
Data Index: 2827434 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0256. Min Range: -9.0256
Max Act: 7.5256. Min Act: -0.1700
Data Index: 4707627 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19