Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1811 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6247. Min Range: -5.6247
Max Act: 5.6247. Min Act: -0.1700
Data Index: 8787759 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.9997. Min Act: -0.1700
Data Index: 7714470 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.9997. Min Act: -0.1700
Data Index: 5549632 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.9059. Min Act: -0.1700
Data Index: 4742216 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.9372. Min Act: -0.1700
Data Index: 5701073 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8747. Min Act: -0.1700
Data Index: 7978627 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8434. Min Act: -0.1700
Data Index: 4366769 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8434. Min Act: -0.1700
Data Index: 102043 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8747. Min Act: -0.1700
Data Index: 2194595 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8434. Min Act: -0.1700
Data Index: 7755887 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8122. Min Act: -0.1700
Data Index: 3045612 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8122. Min Act: -0.1700
Data Index: 3266364 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.8122. Min Act: -0.1700
Data Index: 2200089 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7809. Min Act: -0.1700
Data Index: 7846061 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6283678 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7809. Min Act: -0.1700
Data Index: 3691248 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7184. Min Act: -0.1700
Data Index: 6273254 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7809. Min Act: -0.1700
Data Index: 4745340 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7497. Min Act: -0.1700
Data Index: 7561248 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6247. Min Range: -5.6247
Max Act: 4.7184. Min Act: -0.1700
Data Index: 8171426 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19