Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4155 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.8982. Min Act: -0.1700
Data Index: 1799145 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.8044. Min Act: -0.1700
Data Index: 8539377 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.6167. Min Act: -0.1700
Data Index: 3413605 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.5698. Min Act: -0.1700
Data Index: 1682439 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.5541. Min Act: -0.1700
Data Index: 1682435 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4601. Min Act: -0.1700
Data Index: 7206922 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4758. Min Act: -0.1700
Data Index: 2841963 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4601. Min Act: -0.1700
Data Index: 1169281 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4601. Min Act: -0.1700
Data Index: 5170023 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4445. Min Act: -0.1700
Data Index: 2282591 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4601. Min Act: -0.1700
Data Index: 926256 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4445. Min Act: -0.1700
Data Index: 8275090 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1660721 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4445. Min Act: -0.1700
Data Index: 256354 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4288. Min Act: -0.1700
Data Index: 2284857 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4288. Min Act: -0.1700
Data Index: 3188694 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4131. Min Act: -0.1700
Data Index: 3163443 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4288. Min Act: -0.1700
Data Index: 2288549 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4131. Min Act: -0.1700
Data Index: 7784470 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8982. Min Range: -3.8982
Max Act: 3.4288. Min Act: -0.1700
Data Index: 6521253 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19