Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1944 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.2971. Min Act: -0.1700
Data Index: 2307727 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.2346. Min Act: -0.1700
Data Index: 3245565 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.2034. Min Act: -0.1700
Data Index: 577582 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.1721. Min Act: -0.1700
Data Index: 7895711 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.1409. Min Act: -0.1700
Data Index: 1489504 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.0784. Min Act: -0.1700
Data Index: 6908895 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.0471. Min Act: -0.1700
Data Index: 6597593 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2971. Min Range: -5.2971
Max Act: 5.0159. Min Act: -0.1700
Data Index: 6529844 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9846. Min Act: -0.1700
Data Index: 1253979 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9846. Min Act: -0.1700
Data Index: 4978065 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9846. Min Act: -0.1700
Data Index: 7135138 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9534. Min Act: -0.1700
Data Index: 4198448 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9534. Min Act: -0.1700
Data Index: 3075444 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9534. Min Act: -0.1700
Data Index: 7013799 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9534. Min Act: -0.1700
Data Index: 306885 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9534. Min Act: -0.1700
Data Index: 3907489 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.8909. Min Act: -0.1700
Data Index: 2089141 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.8909. Min Act: -0.1700
Data Index: 1448886 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9221. Min Act: -0.1700
Data Index: 2550046 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2971. Min Range: -5.2971
Max Act: 4.9221. Min Act: -0.1700
Data Index: 7867283 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19