Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.7894. Min Act: -0.1700
Data Index: 3711875 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.7894. Min Act: -0.1700
Data Index: 8662540 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.7269. Min Act: -0.1700
Data Index: 3945343 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.6957. Min Act: -0.1700
Data Index: 3945331 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.6644. Min Act: -0.1700
Data Index: 4725067 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.6332. Min Act: -0.1700
Data Index: 7433786 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.5707. Min Act: -0.1700
Data Index: 7101396 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.5707. Min Act: -0.1700
Data Index: 8036739 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.5707. Min Act: -0.1700
Data Index: 6702457 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.5394. Min Act: -0.1700
Data Index: 1937723 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.4457. Min Act: -0.1700
Data Index: 2221143 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.4144. Min Act: -0.1700
Data Index: 670058 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3832. Min Act: -0.1700
Data Index: 7099483 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3519. Min Act: -0.1700
Data Index: 545951 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3519. Min Act: -0.1700
Data Index: 5921034 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3286992 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3519. Min Act: -0.1700
Data Index: 4213888 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3026330 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3207. Min Act: -0.1700
Data Index: 7245497 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7894. Min Range: -4.7894
Max Act: 4.3207. Min Act: -0.1700
Data Index: 436338 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19