Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.5033. Min Act: -0.1700
Data Index: 6866361 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.4408. Min Act: -0.1700
Data Index: 1049475 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.4408. Min Act: -0.1700
Data Index: 865704 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.3783. Min Act: -0.1700
Data Index: 2500453 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.3783. Min Act: -0.1700
Data Index: 8323519 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.3158. Min Act: -0.1700
Data Index: 7347499 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.3158. Min Act: -0.1700
Data Index: 3571365 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.3158. Min Act: -0.1700
Data Index: 5723270 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.1908. Min Act: -0.1700
Data Index: 3135514 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.1908. Min Act: -0.1700
Data Index: 2555845 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.1595. Min Act: -0.1700
Data Index: 7338224 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.1595. Min Act: -0.1700
Data Index: 5399331 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.1283. Min Act: -0.1700
Data Index: 4967580 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.0970. Min Act: -0.1700
Data Index: 1834698 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.0658. Min Act: -0.1700
Data Index: 340243 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.0658. Min Act: -0.1700
Data Index: 7509171 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.0658. Min Act: -0.1700
Data Index: 5607762 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.0033. Min Act: -0.1700
Data Index: 3294956 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5033. Min Range: -8.5033
Max Act: 8.0345. Min Act: -0.1700
Data Index: 5018547 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5033. Min Range: -8.5033
Max Act: 7.9720. Min Act: -0.1700
Data Index: 24079 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19