Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0010. Min Range: -5.0010
Max Act: 5.0010. Min Act: -0.1700
Data Index: 5203662 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.9385. Min Act: -0.1700
Data Index: 4914946 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.9073. Min Act: -0.1700
Data Index: 3329589 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 3093390 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 5037736 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.7823. Min Act: -0.1700
Data Index: 4745738 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.7823. Min Act: -0.1700
Data Index: 7914762 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.7198. Min Act: -0.1700
Data Index: 6268659 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.6573. Min Act: -0.1700
Data Index: 8637108 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5635. Min Act: -0.1700
Data Index: 2129435 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5323. Min Act: -0.1700
Data Index: 116370 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5635. Min Act: -0.1700
Data Index: 2761590 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5635. Min Act: -0.1700
Data Index: 4955046 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5323. Min Act: -0.1700
Data Index: 1976389 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5323. Min Act: -0.1700
Data Index: 3609453 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5323. Min Act: -0.1700
Data Index: 1558098 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5323. Min Act: -0.1700
Data Index: 3355551 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5323. Min Act: -0.1700
Data Index: 4255026 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5010. Min Act: -0.1700
Data Index: 5586062 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.5010. Min Act: -0.1700
Data Index: 6094553 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19