Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1444 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0803. Min Range: -5.0803
Max Act: 5.0803. Min Act: -0.1700
Data Index: 6085171 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9866. Min Act: -0.1700
Data Index: 254664 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9866. Min Act: -0.1700
Data Index: 1328742 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9553. Min Act: -0.1700
Data Index: 8363096 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5259870 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9553. Min Act: -0.1700
Data Index: 2857618 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5579391 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9241. Min Act: -0.1700
Data Index: 4338321 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.9241. Min Act: -0.1700
Data Index: 7911112 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8928. Min Act: -0.1700
Data Index: 7572822 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 5140892 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 6500573 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 2223236 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 8125579 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 1260985 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 6119737 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 989402 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 3700248 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7991. Min Act: -0.1700
Data Index: 4045886 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7678. Min Act: -0.1700
Data Index: 678739 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19