Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4686. Min Act: -0.1700
Data Index: 550568 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4373. Min Act: -0.1700
Data Index: 6114193 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4373. Min Act: -0.1700
Data Index: 1267680 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4373. Min Act: -0.1700
Data Index: 8711367 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4061. Min Act: -0.1700
Data Index: 3211359 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4061. Min Act: -0.1700
Data Index: 530956 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.4061. Min Act: -0.1700
Data Index: 6420584 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.3436. Min Act: -0.1700
Data Index: 4268048 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.3748. Min Act: -0.1700
Data Index: 8711366 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.3748. Min Act: -0.1700
Data Index: 7502610 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2811. Min Act: -0.1700
Data Index: 3007794 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2811. Min Act: -0.1700
Data Index: 8531170 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2811. Min Act: -0.1700
Data Index: 8626429 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2498. Min Act: -0.1700
Data Index: 6359420 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2498. Min Act: -0.1700
Data Index: 6114194 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2186. Min Act: -0.1700
Data Index: 300829 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2186. Min Act: -0.1700
Data Index: 77996 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2186. Min Act: -0.1700
Data Index: 1442350 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2186. Min Act: -0.1700
Data Index: 4476296 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4686. Min Range: -5.4686
Max Act: 5.2186. Min Act: -0.1700
Data Index: 830484 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19