Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1037 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.2850. Min Act: -0.1700
Data Index: 7713998 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.1600. Min Act: -0.1700
Data Index: 4347082 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0663. Min Act: -0.1700
Data Index: 2346097 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.1288. Min Act: -0.1700
Data Index: 2435689 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0663. Min Act: -0.1700
Data Index: 8278478 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0663. Min Act: -0.1700
Data Index: 2090515 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0350. Min Act: -0.1700
Data Index: 2667652 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0663. Min Act: -0.1700
Data Index: 5616796 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0038. Min Act: -0.1700
Data Index: 7943020 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0350. Min Act: -0.1692
Data Index: 4111657 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9725. Min Act: -0.1700
Data Index: 2490496 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2850. Min Range: -5.2850
Max Act: 5.0038. Min Act: -0.1694
Data Index: 6103250 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9725. Min Act: -0.1699
Data Index: 7302463 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9413. Min Act: -0.1700
Data Index: 62672 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9413. Min Act: -0.1700
Data Index: 824763 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9413. Min Act: -0.1694
Data Index: 7726305 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9413. Min Act: -0.1700
Data Index: 1100370 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.9413. Min Act: -0.1700
Data Index: 7040854 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.8475. Min Act: -0.1700
Data Index: 4231476 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2850. Min Range: -5.2850
Max Act: 4.8475. Min Act: -0.1700
Data Index: 3145424 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19