Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1301 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.3436. Min Act: -0.1698
Data Index: 1721781 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.3083. Min Act: -0.1698
Data Index: 4758963 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2907. Min Act: -0.1700
Data Index: 1375581 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2730. Min Act: -0.1699
Data Index: 6331322 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2730. Min Act: -0.1690
Data Index: 7162779 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2554. Min Act: -0.1667
Data Index: 7180851 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2378. Min Act: -0.1700
Data Index: 692143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2378. Min Act: -0.1700
Data Index: 6949432 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2378. Min Act: -0.1696
Data Index: 1833951 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2201. Min Act: -0.1700
Data Index: 5154739 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2201. Min Act: -0.1687
Data Index: 7393928 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2201. Min Act: -0.1700
Data Index: 1326388 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2201. Min Act: -0.1696
Data Index: 570216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.1849. Min Act: -0.1700
Data Index: 4911606 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.1849. Min Act: -0.1700
Data Index: 4058147 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.1849. Min Act: -0.1700
Data Index: 5469840 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.1849. Min Act: -0.1700
Data Index: 1262589 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2025. Min Act: -0.1700
Data Index: 5940933 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.2025. Min Act: -0.1700
Data Index: 2032727 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3436. Min Range: -1.3436
Max Act: 1.1497. Min Act: -0.1700
Data Index: 3700106 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19