Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4293 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.9703. Min Act: -0.1700
Data Index: 8679538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.9390. Min Act: -0.1698
Data Index: 8618237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4236797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2054178 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2640747 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2537544 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 1544800 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 3494437 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2533251 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1699
Data Index: 437562 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1698
Data Index: 1206928 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4114156 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1674
Data Index: 1170593 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 1073939 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2332044 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4273354 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 976333 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1679
Data Index: 11965 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2240139 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9703. Min Range: -4.9703
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2777116 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19