Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.6022. Min Act: -0.1700
Data Index: 5306794 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.4460. Min Act: -0.1700
Data Index: 2849363 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.4147. Min Act: -0.1700
Data Index: 1285607 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.2897. Min Act: -0.1700
Data Index: 3112374 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.2897. Min Act: -0.1700
Data Index: 52209 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.2272. Min Act: -0.1700
Data Index: 3639560 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.1647. Min Act: -0.1700
Data Index: 3725632 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6022. Min Range: -6.6022
Max Act: 6.1335. Min Act: -0.1700
Data Index: 1314957 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.9460. Min Act: -0.1700
Data Index: 832386 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.8522. Min Act: -0.1700
Data Index: 2765068 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.7897. Min Act: -0.1700
Data Index: 6701000 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.7272. Min Act: -0.1700
Data Index: 79563 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8226871 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6647. Min Act: -0.1700
Data Index: 1284125 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6335. Min Act: -0.1700
Data Index: 7893035 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6335. Min Act: -0.1700
Data Index: 3321848 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6335. Min Act: -0.1700
Data Index: 2061800 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6335. Min Act: -0.1700
Data Index: 6656305 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6022. Min Act: -0.1700
Data Index: 1412246 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6022. Min Range: -6.6022
Max Act: 5.6335. Min Act: -0.1700
Data Index: 5512581 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19