Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4604. Min Act: -0.1571
Data Index: 2538991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4604. Min Act: -0.1627
Data Index: 7875997 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4428. Min Act: -0.1439
Data Index: 3320371 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4340. Min Act: -0.1566
Data Index: 4657499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4252. Min Act: -0.1549
Data Index: 112716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4076. Min Act: -0.1624
Data Index: 3364783 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.4164. Min Act: -0.1320
Data Index: 5760538 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3988. Min Act: -0.1611
Data Index: 1789697 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3988. Min Act: -0.1642
Data Index: 5552480 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3900. Min Act: -0.1615
Data Index: 2046866 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3900. Min Act: -0.1459
Data Index: 4752439 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3988. Min Act: -0.1496
Data Index: 694293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3988. Min Act: -0.1640
Data Index: 4755589 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3724. Min Act: -0.1285
Data Index: 3645081 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3812. Min Act: -0.1554
Data Index: 4854510 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3812. Min Act: -0.1357
Data Index: 5598742 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3724. Min Act: -0.1171
Data Index: 5760539 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3812. Min Act: -0.1586
Data Index: 1909834 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3900. Min Act: -0.1629
Data Index: 8663442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4604. Min Range: -1.4604
Max Act: 1.3812. Min Act: -0.1544
Data Index: 7853152 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19