Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4544 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.5158. Min Act: -0.1700
Data Index: 4396645 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2971. Min Act: -0.1700
Data Index: 2862084 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2971. Min Act: -0.1700
Data Index: 1995053 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2971. Min Act: -0.1700
Data Index: 1736147 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2658. Min Act: -0.1700
Data Index: 4803161 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2658. Min Act: -0.1700
Data Index: 6528247 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2346. Min Act: -0.1700
Data Index: 8738466 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2346. Min Act: -0.1700
Data Index: 7836848 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2033. Min Act: -0.1700
Data Index: 1149507 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2033. Min Act: -0.1700
Data Index: 5318897 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2033. Min Act: -0.1700
Data Index: 2034850 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1721. Min Act: -0.1700
Data Index: 7974522 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1721. Min Act: -0.1700
Data Index: 8738459 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.2033. Min Act: -0.1700
Data Index: 2689213 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1721. Min Act: -0.1700
Data Index: 998230 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1408. Min Act: -0.1700
Data Index: 8604331 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1408. Min Act: -0.1700
Data Index: 7190619 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1408. Min Act: -0.1700
Data Index: 622325 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1096. Min Act: -0.1700
Data Index: 8723549 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5158. Min Range: -5.5158
Max Act: 5.1096. Min Act: -0.1700
Data Index: 888507 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19