Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4658 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.8830. Min Act: -0.1700
Data Index: 7660144 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7892. Min Act: -0.1700
Data Index: 663028 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7580. Min Act: -0.1700
Data Index: 791154 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7267. Min Act: -0.1700
Data Index: 4112713 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7267. Min Act: -0.1700
Data Index: 3187661 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6955. Min Act: -0.1700
Data Index: 5109525 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6642. Min Act: -0.1700
Data Index: 7214202 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6642. Min Act: -0.1700
Data Index: 6051363 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6642. Min Act: -0.1700
Data Index: 6539473 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6642. Min Act: -0.1700
Data Index: 6263845 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6017. Min Act: -0.1700
Data Index: 6095105 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5705. Min Act: -0.1700
Data Index: 286153 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 1072764 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 6792779 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 1327053 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5392. Min Act: -0.1700
Data Index: 4994952 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 8258702 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 7898217 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 7297548 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 275852 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19