Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.3210. Min Act: -0.1700
Data Index: 1530242 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.2898. Min Act: -0.1700
Data Index: 6677318 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.2273. Min Act: -0.1700
Data Index: 4080321 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.1960. Min Act: -0.1700
Data Index: 4891016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.1960. Min Act: -0.1700
Data Index: 8435287 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.1648. Min Act: -0.1700
Data Index: 185732 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.1648. Min Act: -0.1700
Data Index: 5377038 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.0710. Min Act: -0.1700
Data Index: 4503078 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.0710. Min Act: -0.1700
Data Index: 8235423 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.0710. Min Act: -0.1700
Data Index: 1864308 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.0710. Min Act: -0.1700
Data Index: 8057403 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.0085. Min Act: -0.1700
Data Index: 1067400 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9772. Min Act: -0.1700
Data Index: 8343222 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9772. Min Act: -0.1700
Data Index: 1301464 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3210. Min Range: -4.3210
Max Act: 4.0085. Min Act: -0.1700
Data Index: 1678100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9460. Min Act: -0.1700
Data Index: 587411 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9460. Min Act: -0.1700
Data Index: 5719265 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9460. Min Act: -0.1700
Data Index: 7989065 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9460. Min Act: -0.1700
Data Index: 8390405 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3210. Min Range: -4.3210
Max Act: 3.9147. Min Act: -0.1700
Data Index: 6305796 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19