Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2177 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.4642. Min Act: -0.1700
Data Index: 1765202 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.4017. Min Act: -0.1700
Data Index: 716148 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.3705. Min Act: -0.1700
Data Index: 3284761 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.3080. Min Act: -0.1700
Data Index: 1195212 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2767. Min Act: -0.1700
Data Index: 366185 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2455. Min Act: -0.1700
Data Index: 1820422 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 823820 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 4177962 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 4908606 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 2659401 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 8826529 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 1270087 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 6433051 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 105588 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 605354 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 1200468 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 8129910 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 1552949 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1517. Min Act: -0.1700
Data Index: 1460863 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1517. Min Act: -0.1700
Data Index: 31564 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19