Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2136 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.8173. Min Act: -0.1700
Data Index: 5669246 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.5673. Min Act: -0.1700
Data Index: 8136833 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.4423. Min Act: -0.1700
Data Index: 6139515 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.3798. Min Act: -0.1700
Data Index: 2749552 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.1298. Min Act: -0.1700
Data Index: 3493507 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.0673. Min Act: -0.1700
Data Index: 5481504 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.0673. Min Act: -0.1700
Data Index: 1483874 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.0048. Min Act: -0.1700
Data Index: 2805489 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.9423. Min Act: -0.1700
Data Index: 501817 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.9423. Min Act: -0.1700
Data Index: 2749551 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.8173. Min Range: -15.8173
Max Act: 15.0048. Min Act: -0.1700
Data Index: 5071665 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 1551810 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 203177 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 3473512 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 1551811 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 5717288 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 5669248 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8173. Min Act: -0.1700
Data Index: 745072 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.8798. Min Act: -0.1700
Data Index: 6458262 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.8173. Min Range: -15.8173
Max Act: 14.7548. Min Act: -0.1700
Data Index: 745068 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19