Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0104. Min Range: -5.0104
Max Act: 5.0104. Min Act: -0.1700
Data Index: 5591227 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.8229. Min Act: -0.1700
Data Index: 3444190 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.6979. Min Act: -0.1700
Data Index: 8696924 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.6667. Min Act: -0.1700
Data Index: 4891642 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.6042. Min Act: -0.1700
Data Index: 4232275 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.6042. Min Act: -0.1700
Data Index: 2442337 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.5729. Min Act: -0.1700
Data Index: 3259701 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.5104. Min Act: -0.1700
Data Index: 4479652 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.5104. Min Act: -0.1700
Data Index: 6124059 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.4792. Min Act: -0.1700
Data Index: 4958484 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.5104. Min Act: -0.1700
Data Index: 6514484 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.4167. Min Act: -0.1700
Data Index: 6940155 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.4167. Min Act: -0.1700
Data Index: 5143883 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.4167. Min Act: -0.1700
Data Index: 8558621 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.4167. Min Act: -0.1700
Data Index: 8139910 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.3854. Min Act: -0.1700
Data Index: 5677706 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.3854. Min Act: -0.1700
Data Index: 4368927 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.3542. Min Act: -0.1700
Data Index: 2248189 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.3542. Min Act: -0.1700
Data Index: 6891391 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0104. Min Range: -5.0104
Max Act: 4.3229. Min Act: -0.1700
Data Index: 5301221 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19