Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.1622. Min Act: -0.1700
Data Index: 930934 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.0685. Min Act: -0.1700
Data Index: 1924341 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.0685. Min Act: -0.1700
Data Index: 7423675 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.1310. Min Act: -0.1700
Data Index: 6594019 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.0372. Min Act: -0.1700
Data Index: 1441999 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.0685. Min Act: -0.1700
Data Index: 274484 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1622. Min Range: -5.1622
Max Act: 5.0060. Min Act: -0.1700
Data Index: 4017072 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9747. Min Act: -0.1700
Data Index: 1811395 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9747. Min Act: -0.1700
Data Index: 4983700 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 2833814 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 4805885 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 5771449 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 176173 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 7046545 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9122. Min Act: -0.1700
Data Index: 3454103 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.9122. Min Act: -0.1700
Data Index: 2675199 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.8810. Min Act: -0.1700
Data Index: 8340488 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.8810. Min Act: -0.1700
Data Index: 7605830 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.8810. Min Act: -0.1700
Data Index: 3881929 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1622. Min Range: -5.1622
Max Act: 4.8497. Min Act: -0.1700
Data Index: 6631196 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19