Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 2429687 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3567. Min Act: -0.1700
Data Index: 955754 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.3567. Min Act: -0.1700
Data Index: 1295127 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2942. Min Act: -0.1700
Data Index: 8721481 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 4760578 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2630. Min Act: -0.1700
Data Index: 7508050 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2317. Min Act: -0.1700
Data Index: 4624379 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2317. Min Act: -0.1700
Data Index: 7764454 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2005. Min Act: -0.1700
Data Index: 1209964 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.2317. Min Act: -0.1700
Data Index: 3680489 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1692. Min Act: -0.1700
Data Index: 126315 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 3382874 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1067. Min Act: -0.1700
Data Index: 1300927 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1617465 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1214117 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1539956 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.1380. Min Act: -0.1700
Data Index: 2083904 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0755. Min Act: -0.1700
Data Index: 5021686 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0442. Min Act: -0.1700
Data Index: 5898639 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5130. Min Range: -5.5130
Max Act: 5.0755. Min Act: -0.1700
Data Index: 6813421 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19