Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.3095. Min Act: -0.1700
Data Index: 8209500 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.3095. Min Act: -0.1700
Data Index: 6934799 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.2158. Min Act: -0.1700
Data Index: 4183411 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1845. Min Act: -0.1700
Data Index: 251909 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1845. Min Act: -0.1700
Data Index: 1989021 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1532. Min Act: -0.1700
Data Index: 936916 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1845. Min Act: -0.1700
Data Index: 5557081 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1532. Min Act: -0.1700
Data Index: 530875 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3282719 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1845. Min Act: -0.1700
Data Index: 301533 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1220. Min Act: -0.1700
Data Index: 7234870 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1532. Min Act: -0.1700
Data Index: 6374971 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1220. Min Act: -0.1700
Data Index: 3650570 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1532. Min Act: -0.1700
Data Index: 3514830 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1532. Min Act: -0.1700
Data Index: 7343988 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.0907. Min Act: -0.1700
Data Index: 2966189 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1220. Min Act: -0.1700
Data Index: 3896156 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1532. Min Act: -0.1700
Data Index: 4010652 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.0907. Min Act: -0.1700
Data Index: 5927469 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3095. Min Range: -4.3095
Max Act: 4.1220. Min Act: -0.1700
Data Index: 5961023 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19