Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5697 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.3909. Min Act: -0.1700
Data Index: 7769122 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.2659. Min Act: -0.1700
Data Index: 5047420 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.1721. Min Act: -0.1700
Data Index: 199226 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.1409. Min Act: -0.1700
Data Index: 7120954 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.0784. Min Act: -0.1700
Data Index: 1049859 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.0159. Min Act: -0.1700
Data Index: 8417967 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3909. Min Range: -5.3909
Max Act: 5.0471. Min Act: -0.1700
Data Index: 921781 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9846. Min Act: -0.1700
Data Index: 6205685 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9846. Min Act: -0.1700
Data Index: 5300542 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9846. Min Act: -0.1700
Data Index: 4923173 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9846. Min Act: -0.1700
Data Index: 1468196 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9846. Min Act: -0.1700
Data Index: 1421080 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9534. Min Act: -0.1700
Data Index: 5079245 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9534. Min Act: -0.1700
Data Index: 7679223 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9221. Min Act: -0.1700
Data Index: 389892 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9221. Min Act: -0.1700
Data Index: 3824190 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.9221. Min Act: -0.1700
Data Index: 2555903 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.8909. Min Act: -0.1700
Data Index: 6925610 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.8909. Min Act: -0.1700
Data Index: 5188762 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3909. Min Range: -5.3909
Max Act: 4.8909. Min Act: -0.1700
Data Index: 7542878 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19