Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4908. Min Range: -7.4908
Max Act: 7.4908. Min Act: -0.1700
Data Index: 4660299 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4908. Min Range: -7.4908
Max Act: 7.0533. Min Act: -0.1700
Data Index: 8343443 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.8970. Min Act: -0.1700
Data Index: 169497 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8715761 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.7720. Min Act: -0.1700
Data Index: 4660298 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.7095. Min Act: -0.1700
Data Index: 7197669 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.6470. Min Act: -0.1700
Data Index: 5600261 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.6470. Min Act: -0.1700
Data Index: 4660300 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.6158. Min Act: -0.1700
Data Index: 4748282 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.5220. Min Act: -0.1700
Data Index: 7670713 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.5220. Min Act: -0.1700
Data Index: 2050822 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.5220. Min Act: -0.1700
Data Index: 2444440 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.4595. Min Act: -0.1700
Data Index: 3310471 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.4908. Min Act: -0.1700
Data Index: 7434805 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.4908. Min Act: -0.1700
Data Index: 269888 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.4908. Min Act: -0.1700
Data Index: 5426478 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.4283. Min Act: -0.1700
Data Index: 6827693 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.4595. Min Act: -0.1700
Data Index: 2433469 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.3970. Min Act: -0.1700
Data Index: 3659064 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4908. Min Range: -7.4908
Max Act: 6.3658. Min Act: -0.1700
Data Index: 2105866 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19