Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2526 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.7696. Min Act: -0.1700
Data Index: 3534294 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.7383. Min Act: -0.1700
Data Index: 1424401 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.7071. Min Act: -0.1700
Data Index: 410509 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.6758. Min Act: -0.1700
Data Index: 334460 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.6133. Min Act: -0.1700
Data Index: 7370543 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.6133. Min Act: -0.1700
Data Index: 4250162 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.5821. Min Act: -0.1700
Data Index: 3534276 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.5821. Min Act: -0.1700
Data Index: 7385700 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.5508. Min Act: -0.1700
Data Index: 7127028 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.5821. Min Act: -0.1700
Data Index: 3534279 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.5508. Min Act: -0.1700
Data Index: 1297940 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1190011 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4883. Min Act: -0.1700
Data Index: 7668818 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4883. Min Act: -0.1700
Data Index: 3295172 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4258. Min Act: -0.1700
Data Index: 932816 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4571. Min Act: -0.1700
Data Index: 3534295 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4571. Min Act: -0.1700
Data Index: 2146956 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4883. Min Act: -0.1700
Data Index: 3719028 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4258. Min Act: -0.1700
Data Index: 1828324 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7696. Min Range: -5.7696
Max Act: 5.4258. Min Act: -0.1700
Data Index: 653771 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19