Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0415. Min Range: -5.0415
Max Act: 5.0415. Min Act: -0.1700
Data Index: 2608360 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.8540. Min Act: -0.1700
Data Index: 2088075 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.7603. Min Act: -0.1700
Data Index: 5742790 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.7290. Min Act: -0.1700
Data Index: 7870811 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.6665. Min Act: -0.1700
Data Index: 5742795 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5742778 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.6040. Min Act: -0.1700
Data Index: 7852940 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.6040. Min Act: -0.1700
Data Index: 5841263 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.6040. Min Act: -0.1700
Data Index: 146162 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5728. Min Act: -0.1700
Data Index: 4108933 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5728. Min Act: -0.1700
Data Index: 7870810 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5728. Min Act: -0.1700
Data Index: 5742787 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5728. Min Act: -0.1700
Data Index: 2088088 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5728. Min Act: -0.1700
Data Index: 3394808 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5415. Min Act: -0.1700
Data Index: 2088098 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5103. Min Act: -0.1700
Data Index: 882244 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5103. Min Act: -0.1700
Data Index: 2088077 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.5103. Min Act: -0.1700
Data Index: 131066 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.4790. Min Act: -0.1700
Data Index: 172077 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0415. Min Range: -5.0415
Max Act: 4.4165. Min Act: -0.1700
Data Index: 882243 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19