Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1412 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.6800. Min Act: -0.1700
Data Index: 1125874 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.6800. Min Act: -0.1700
Data Index: 2509485 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.6800. Min Act: -0.1700
Data Index: 2674483 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.6175. Min Act: -0.1700
Data Index: 502416 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.6175. Min Act: -0.1700
Data Index: 3191468 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.5550. Min Act: -0.1700
Data Index: 5710033 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.5550. Min Act: -0.1700
Data Index: 386958 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.5550. Min Act: -0.1700
Data Index: 386955 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.4925. Min Act: -0.1700
Data Index: 3425329 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.4925. Min Act: -0.1700
Data Index: 1475571 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.4300. Min Act: -0.1700
Data Index: 448073 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.3675. Min Act: -0.1700
Data Index: 3134096 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.3675. Min Act: -0.1700
Data Index: 22555 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.3050. Min Act: -0.1700
Data Index: 3408573 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.3050. Min Act: -0.1700
Data Index: 2182107 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.2425. Min Act: -0.1700
Data Index: 1816576 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.1800. Min Act: -0.1700
Data Index: 3928317 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.1800. Min Act: -0.1700
Data Index: 1440357 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.1800. Min Act: -0.1700
Data Index: 6664377 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6800. Min Range: -8.6800
Max Act: 8.1800. Min Act: -0.1700
Data Index: 6268871 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19