Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.9104. Min Act: -0.1700
Data Index: 8654246 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.8478. Min Act: -0.1700
Data Index: 6986575 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.8635. Min Act: -0.1700
Data Index: 1123353 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.8478. Min Act: -0.1700
Data Index: 6525483 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.8009. Min Act: -0.1700
Data Index: 144286 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.7540. Min Act: -0.1700
Data Index: 1800937 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.7540. Min Act: -0.1700
Data Index: 2868635 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.7071. Min Act: -0.1700
Data Index: 7350014 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.6289. Min Act: -0.1700
Data Index: 3658991 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.5350. Min Act: -0.1700
Data Index: 1814684 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.4723. Min Act: -0.1700
Data Index: 8034480 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.4723. Min Act: -0.1700
Data Index: 2595380 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.4253. Min Act: -0.1700
Data Index: 370969 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.3939. Min Act: -0.1700
Data Index: 7539821 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.3939. Min Act: -0.1700
Data Index: 5467821 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.3626. Min Act: -0.1700
Data Index: 5444627 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.3469. Min Act: -0.1700
Data Index: 5378545 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.3312. Min Act: -0.1700
Data Index: 1617565 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.3312. Min Act: -0.1700
Data Index: 1363278 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9104. Min Range: -3.9104
Max Act: 3.2841. Min Act: -0.1700
Data Index: 3019304 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19