Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7684. Min Act: -0.1700
Data Index: 6456213 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7371. Min Act: -0.1700
Data Index: 2768441 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7059. Min Act: -0.1700
Data Index: 8629354 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7059. Min Act: -0.1700
Data Index: 2616853 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7059. Min Act: -0.1700
Data Index: 7779297 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7059. Min Act: -0.1700
Data Index: 845758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 6920954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 6500011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.7059. Min Act: -0.1700
Data Index: 6020362 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 2166730 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 2116615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 5278520 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 4697413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 4504141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 1128703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 1114485 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 4251235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 3135553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 2946179 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7684. Min Range: -3.7684
Max Act: 3.6746. Min Act: -0.1700
Data Index: 2686640 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19