Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.2804. Min Act: -0.1700
Data Index: 1154118 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.1861. Min Act: -0.1700
Data Index: 2035376 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.1547. Min Act: -0.1700
Data Index: 8562245 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.1232. Min Act: -0.1700
Data Index: 2928494 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0127. Min Act: -0.1700
Data Index: 7474941 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0916. Min Act: -0.1700
Data Index: 3732932 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0759. Min Act: -0.1700
Data Index: 675201 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0285. Min Act: -0.1700
Data Index: 7974673 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0285. Min Act: -0.1700
Data Index: 4423418 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0285. Min Act: -0.1700
Data Index: 8687310 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.1074. Min Act: -0.1700
Data Index: 8797428 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0127. Min Act: -0.1700
Data Index: 739927 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0127. Min Act: -0.1700
Data Index: 8794389 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2804. Min Range: -3.2804
Max Act: 2.9811. Min Act: -0.1700
Data Index: 7667242 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2804. Min Range: -3.2804
Max Act: 2.9811. Min Act: -0.1700
Data Index: 4255500 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2804. Min Range: -3.2804
Max Act: 3.0127. Min Act: -0.1700
Data Index: 7729700 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2804. Min Range: -3.2804
Max Act: 2.9178. Min Act: -0.1700
Data Index: 6068157 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2804. Min Range: -3.2804
Max Act: 2.9495. Min Act: -0.1700
Data Index: 506524 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2804. Min Range: -3.2804
Max Act: 2.9020. Min Act: -0.1700
Data Index: 2346778 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2804. Min Range: -3.2804
Max Act: 2.9020. Min Act: -0.1700
Data Index: 1738759 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19