Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6160. Min Range: -6.6160
Max Act: 6.6160. Min Act: -0.1700
Data Index: 5659169 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6160. Min Range: -6.6160
Max Act: 6.2097. Min Act: -0.1700
Data Index: 4897725 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6160. Min Range: -6.6160
Max Act: 6.0222. Min Act: -0.1700
Data Index: 2567795 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6160. Min Range: -6.6160
Max Act: 6.0222. Min Act: -0.1700
Data Index: 7048001 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9597. Min Act: -0.1700
Data Index: 2807047 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9597. Min Act: -0.1700
Data Index: 6381575 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3501908 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 228977 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6382322 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6791415 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.9285. Min Act: -0.1700
Data Index: 3096606 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8660. Min Act: -0.1700
Data Index: 5334352 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8972. Min Act: -0.1700
Data Index: 7515524 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8972. Min Act: -0.1700
Data Index: 8715634 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8972. Min Act: -0.1700
Data Index: 3201878 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8035. Min Act: -0.1700
Data Index: 6065375 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8347. Min Act: -0.1700
Data Index: 8465828 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8035. Min Act: -0.1700
Data Index: 1074007 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.8035. Min Act: -0.1700
Data Index: 5730489 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6160. Min Range: -6.6160
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3211289 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19