Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.2734. Min Act: -0.1700
Data Index: 4913727 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.1796. Min Act: -0.1700
Data Index: 2814393 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.1796. Min Act: -0.1700
Data Index: 7292793 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.1484. Min Act: -0.1700
Data Index: 688504 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.1484. Min Act: -0.1700
Data Index: 3490495 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.1484. Min Act: -0.1700
Data Index: 2847004 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0859. Min Act: -0.1700
Data Index: 6970119 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0859. Min Act: -0.1700
Data Index: 8566758 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0546. Min Act: -0.1700
Data Index: 2814387 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0546. Min Act: -0.1700
Data Index: 3930051 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0546. Min Act: -0.1700
Data Index: 8385664 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0546. Min Act: -0.1700
Data Index: 7033685 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0546. Min Act: -0.1700
Data Index: 290648 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0546. Min Act: -0.1700
Data Index: 7536973 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2734. Min Range: -4.2734
Max Act: 3.9921. Min Act: -0.1700
Data Index: 1778436 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0233. Min Act: -0.1700
Data Index: 1220103 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2734. Min Range: -4.2734
Max Act: 4.0233. Min Act: -0.1700
Data Index: 4148241 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2734. Min Range: -4.2734
Max Act: 3.9608. Min Act: -0.1700
Data Index: 6291746 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2734. Min Range: -4.2734
Max Act: 3.9608. Min Act: -0.1700
Data Index: 721755 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2734. Min Range: -4.2734
Max Act: 3.9296. Min Act: -0.1700
Data Index: 2814380 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19