Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2307 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.6885. Min Act: -0.1700
Data Index: 4829021 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.6260. Min Act: -0.1700
Data Index: 5233250 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.5635. Min Act: -0.1700
Data Index: 5094849 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.5635. Min Act: -0.1700
Data Index: 2765177 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.5322. Min Act: -0.1700
Data Index: 1159475 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.5322. Min Act: -0.1700
Data Index: 6677483 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.5322. Min Act: -0.1700
Data Index: 105579 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4697. Min Act: -0.1700
Data Index: 4259197 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4697. Min Act: -0.1700
Data Index: 1230600 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4697. Min Act: -0.1700
Data Index: 3681163 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4697. Min Act: -0.1700
Data Index: 1387950 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 7158984 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4697. Min Act: -0.1700
Data Index: 3551410 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4072. Min Act: -0.1700
Data Index: 129373 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.4385. Min Act: -0.1700
Data Index: 5882075 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.3760. Min Act: -0.1700
Data Index: 1846961 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.3760. Min Act: -0.1700
Data Index: 2310889 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.3760. Min Act: -0.1700
Data Index: 6190833 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.3135. Min Act: -0.1700
Data Index: 2161347 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6885. Min Range: -7.6885
Max Act: 7.3760. Min Act: -0.1700
Data Index: 4938004 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19