Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.3684. Min Act: -0.1700
Data Index: 4570508 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.3059. Min Act: -0.1700
Data Index: 2500512 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.2747. Min Act: -0.1700
Data Index: 1507209 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.2434. Min Act: -0.1699
Data Index: 718956 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.2434. Min Act: -0.1700
Data Index: 4330971 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.2122. Min Act: -0.1700
Data Index: 8672511 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.2122. Min Act: -0.1700
Data Index: 4067003 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1809. Min Act: -0.1700
Data Index: 3996608 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1809. Min Act: -0.1700
Data Index: 2041656 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1497. Min Act: -0.1700
Data Index: 2787114 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1497. Min Act: -0.1700
Data Index: 2093532 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1497. Min Act: -0.1700
Data Index: 6533329 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1497. Min Act: -0.1700
Data Index: 6668511 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1184. Min Act: -0.1700
Data Index: 5285010 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1184. Min Act: -0.1700
Data Index: 5972161 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.1497. Min Act: -0.1700
Data Index: 4373324 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.0872. Min Act: -0.1700
Data Index: 7105362 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.0872. Min Act: -0.1700
Data Index: 3448111 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.0872. Min Act: -0.1700
Data Index: 3908875 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3684. Min Range: -5.3684
Max Act: 5.0872. Min Act: -0.1700
Data Index: 2130234 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19