Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2614 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.8291. Min Act: -0.1700
Data Index: 1576266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.8291. Min Act: -0.1700
Data Index: 7853938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.8291. Min Act: -0.1700
Data Index: 1003671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 6899314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 8710847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 3908078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 3450514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 3149453 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 7081872 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 6774599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 2492072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 190308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7979. Min Act: -0.1700
Data Index: 1838027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 965755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 7733593 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 6359636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 5360562 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 7905347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 89152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8291. Min Range: -3.8291
Max Act: 3.7666. Min Act: -0.1700
Data Index: 3656626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19