Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1748. Min Range: -9.1748
Max Act: 9.1748. Min Act: -0.1700
Data Index: 5019397 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1748. Min Range: -9.1748
Max Act: 9.1123. Min Act: -0.1700
Data Index: 7007896 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1748. Min Range: -9.1748
Max Act: 9.0498. Min Act: -0.1700
Data Index: 3659468 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1748. Min Range: -9.1748
Max Act: 9.0498. Min Act: -0.1700
Data Index: 35731 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1748. Min Range: -9.1748
Max Act: 9.0498. Min Act: -0.1700
Data Index: 492760 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.9248. Min Act: -0.1700
Data Index: 6363029 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.9248. Min Act: -0.1700
Data Index: 3405777 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.7998. Min Act: -0.1700
Data Index: 3074400 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.7998. Min Act: -0.1700
Data Index: 6572668 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.7998. Min Act: -0.1700
Data Index: 7679523 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.7373. Min Act: -0.1700
Data Index: 6631962 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.7373. Min Act: -0.1700
Data Index: 6898547 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6748. Min Act: -0.1700
Data Index: 3715571 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6123. Min Act: -0.1700
Data Index: 1536197 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6748. Min Act: -0.1700
Data Index: 1203449 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6748. Min Act: -0.1700
Data Index: 2034632 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6748. Min Act: -0.1700
Data Index: 3663245 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6748. Min Act: -0.1700
Data Index: 5411745 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6748. Min Act: -0.1700
Data Index: 3017218 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1748. Min Range: -9.1748
Max Act: 8.6123. Min Act: -0.1700
Data Index: 6702624 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19