Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1777 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3220. Min Range: -8.3220
Max Act: 8.3220. Min Act: -0.1700
Data Index: 5153281 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3220. Min Range: -8.3220
Max Act: 8.0407. Min Act: -0.1700
Data Index: 2534627 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3220. Min Range: -8.3220
Max Act: 8.0407. Min Act: -0.1700
Data Index: 3095198 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3220. Min Range: -8.3220
Max Act: 8.0095. Min Act: -0.1700
Data Index: 3884243 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3220. Min Range: -8.3220
Max Act: 8.0095. Min Act: -0.1700
Data Index: 7093948 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.9782. Min Act: -0.1700
Data Index: 5747203 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.9782. Min Act: -0.1700
Data Index: 1629497 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.9157. Min Act: -0.1700
Data Index: 4091022 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.9470. Min Act: -0.1700
Data Index: 7990775 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.8532. Min Act: -0.1700
Data Index: 5839400 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.8532. Min Act: -0.1700
Data Index: 6964746 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.8220. Min Act: -0.1700
Data Index: 5072830 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.7282. Min Act: -0.1700
Data Index: 6816254 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.7282. Min Act: -0.1700
Data Index: 6170508 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.6970. Min Act: -0.1700
Data Index: 6245195 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.6970. Min Act: -0.1700
Data Index: 2944955 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.6657. Min Act: -0.1700
Data Index: 6596386 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.6657. Min Act: -0.1700
Data Index: 4560159 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.6657. Min Act: -0.1700
Data Index: 3032311 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3220. Min Range: -8.3220
Max Act: 7.6657. Min Act: -0.1700
Data Index: 367682 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19