Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4011 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2707. Min Range: -4.2707
Max Act: 4.2707. Min Act: -0.1700
Data Index: 2950507 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2707. Min Range: -4.2707
Max Act: 4.0832. Min Act: -0.1700
Data Index: 4290913 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2707. Min Range: -4.2707
Max Act: 4.0519. Min Act: -0.1700
Data Index: 4559617 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9894. Min Act: -0.1700
Data Index: 5987717 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9894. Min Act: -0.1700
Data Index: 58198 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9894. Min Act: -0.1700
Data Index: 3141372 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9894. Min Act: -0.1700
Data Index: 1513918 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9582. Min Act: -0.1700
Data Index: 7579209 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1490650 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9582. Min Act: -0.1700
Data Index: 3259443 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9582. Min Act: -0.1700
Data Index: 576563 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1341082 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9269. Min Act: -0.1700
Data Index: 365011 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.9269. Min Act: -0.1700
Data Index: 1258011 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.8644. Min Act: -0.1700
Data Index: 1188120 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.8956. Min Act: -0.1700
Data Index: 4957645 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.8956. Min Act: -0.1700
Data Index: 1463070 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.8956. Min Act: -0.1700
Data Index: 5636613 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.8956. Min Act: -0.1700
Data Index: 5951158 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2707. Min Range: -4.2707
Max Act: 3.8956. Min Act: -0.1700
Data Index: 1739758 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19