Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5435 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.4131. Min Act: -0.1700
Data Index: 5608590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3661. Min Act: -0.1700
Data Index: 8760623 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3661. Min Act: -0.1700
Data Index: 8223081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3347. Min Act: -0.1700
Data Index: 1009448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3190. Min Act: -0.1700
Data Index: 5128028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3190. Min Act: -0.1700
Data Index: 1595493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3190. Min Act: -0.1700
Data Index: 8032577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3033. Min Act: -0.1700
Data Index: 3370638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3033. Min Act: -0.1700
Data Index: 109078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3033. Min Act: -0.1700
Data Index: 4571634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.3033. Min Act: -0.1700
Data Index: 6760734 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2719. Min Act: -0.1700
Data Index: 98071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2562. Min Act: -0.1700
Data Index: 2421492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2562. Min Act: -0.1700
Data Index: 484059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2562. Min Act: -0.1700
Data Index: 6265764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2562. Min Act: -0.1700
Data Index: 1122247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2562. Min Act: -0.1700
Data Index: 6132526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2562. Min Act: -0.1700
Data Index: 2775666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2405. Min Act: -0.1700
Data Index: 2775144 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4131. Min Range: -3.4131
Max Act: 3.2405. Min Act: -0.1700
Data Index: 5925496 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19