Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1189 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.9424. Min Act: -0.1700
Data Index: 8399764 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.7549. Min Act: -0.1700
Data Index: 3944872 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.7237. Min Act: -0.1700
Data Index: 521382 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.7237. Min Act: -0.1700
Data Index: 3570186 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.7237. Min Act: -0.1700
Data Index: 5619202 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.6924. Min Act: -0.1700
Data Index: 1290406 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.6612. Min Act: -0.1700
Data Index: 7334845 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.6612. Min Act: -0.1700
Data Index: 5109289 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5987. Min Act: -0.1700
Data Index: 7465194 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5987. Min Act: -0.1700
Data Index: 7714100 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5987. Min Act: -0.1700
Data Index: 4453351 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5674. Min Act: -0.1700
Data Index: 5485812 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 1899262 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 908648 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 5015737 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 754509 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 3883282 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5674. Min Act: -0.1700
Data Index: 2613198 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 399042 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9424. Min Range: -5.9424
Max Act: 5.5362. Min Act: -0.1700
Data Index: 501097 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19