Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.9593. Min Act: -0.1700
Data Index: 8232425 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.8968. Min Act: -0.1700
Data Index: 3127776 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.8343. Min Act: -0.1700
Data Index: 3672782 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.8343. Min Act: -0.1700
Data Index: 4320062 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.7406. Min Act: -0.1700
Data Index: 6132050 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6781. Min Act: -0.1700
Data Index: 7504490 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6781. Min Act: -0.1700
Data Index: 6622141 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.7093. Min Act: -0.1700
Data Index: 4300310 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6156. Min Act: -0.1700
Data Index: 2361801 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6468. Min Act: -0.1700
Data Index: 4496216 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6468. Min Act: -0.1700
Data Index: 4321732 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.6156. Min Act: -0.1700
Data Index: 2292399 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.5843. Min Act: -0.1700
Data Index: 2928292 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4906. Min Act: -0.1700
Data Index: 3018906 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4906. Min Act: -0.1700
Data Index: 4291075 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4906. Min Act: -0.1700
Data Index: 2806346 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4281. Min Act: -0.1700
Data Index: 399609 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4593. Min Act: -0.1700
Data Index: 310404 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.3968. Min Act: -0.1700
Data Index: 1551473 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9593. Min Range: -7.9593
Max Act: 7.4281. Min Act: -0.1700
Data Index: 2592452 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19