Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.4135. Min Act: -0.1700
Data Index: 1926533 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.4135. Min Act: -0.1700
Data Index: 4511231 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.2573. Min Act: -0.1700
Data Index: 6507677 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1948. Min Act: -0.1700
Data Index: 7316287 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1948. Min Act: -0.1700
Data Index: 518252 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1635. Min Act: -0.1700
Data Index: 8592550 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1635. Min Act: -0.1700
Data Index: 5891220 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1323. Min Act: -0.1700
Data Index: 496240 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1635. Min Act: -0.1700
Data Index: 2108284 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1635. Min Act: -0.1700
Data Index: 2019977 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1323. Min Act: -0.1700
Data Index: 1135403 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1323. Min Act: -0.1700
Data Index: 5233510 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1635. Min Act: -0.1700
Data Index: 4406058 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1323. Min Act: -0.1700
Data Index: 185087 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1323. Min Act: -0.1700
Data Index: 5909520 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0698. Min Act: -0.1700
Data Index: 750368 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1010. Min Act: -0.1700
Data Index: 7068697 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0698. Min Act: -0.1700
Data Index: 6179044 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0698. Min Act: -0.1700
Data Index: 2831937 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1010. Min Act: -0.1700
Data Index: 1203802 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19