Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.5311. Min Act: -0.1700
Data Index: 7682303 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.4373. Min Act: -0.1700
Data Index: 4669555 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.4373. Min Act: -0.1700
Data Index: 6375491 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.4373. Min Act: -0.1700
Data Index: 5011696 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.4373. Min Act: -0.1700
Data Index: 2714249 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.4061. Min Act: -0.1700
Data Index: 6825100 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3436. Min Act: -0.1700
Data Index: 5512214 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3748. Min Act: -0.1700
Data Index: 430490 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3436. Min Act: -0.1700
Data Index: 613981 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3436. Min Act: -0.1700
Data Index: 875541 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3436. Min Act: -0.1700
Data Index: 5577684 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3436. Min Act: -0.1700
Data Index: 1946091 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3123. Min Act: -0.1700
Data Index: 2728012 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3123. Min Act: -0.1700
Data Index: 6100306 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3123. Min Act: -0.1700
Data Index: 62588 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3123. Min Act: -0.1700
Data Index: 2100757 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.3123. Min Act: -0.1700
Data Index: 7728569 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.2811. Min Act: -0.1700
Data Index: 3668534 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.2498. Min Act: -0.1700
Data Index: 5323275 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5311. Min Range: -5.5311
Max Act: 5.2498. Min Act: -0.1700
Data Index: 7268296 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19