Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1143 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.6792. Min Act: -0.1700
Data Index: 93015 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6001271 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.5855. Min Act: -0.1700
Data Index: 2309268 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.4292. Min Act: -0.1700
Data Index: 3971749 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3667. Min Act: -0.1700
Data Index: 1560812 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3667. Min Act: -0.1700
Data Index: 2019074 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3355. Min Act: -0.1700
Data Index: 7997619 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3042. Min Act: -0.1700
Data Index: 1902883 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3355. Min Act: -0.1700
Data Index: 8457709 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3042. Min Act: -0.1700
Data Index: 5515222 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2730. Min Act: -0.1700
Data Index: 7747167 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3042. Min Act: -0.1700
Data Index: 277454 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.3042. Min Act: -0.1700
Data Index: 435500 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2730. Min Act: -0.1700
Data Index: 2448049 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2417. Min Act: -0.1700
Data Index: 1924545 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2417. Min Act: -0.1700
Data Index: 6282418 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2105. Min Act: -0.1700
Data Index: 3075583 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2105. Min Act: -0.1700
Data Index: 8664152 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.2105. Min Act: -0.1700
Data Index: 7256166 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6792. Min Range: -6.6792
Max Act: 6.1792. Min Act: -0.1700
Data Index: 5519214 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19