Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.9062. Min Act: -0.1700
Data Index: 3527095 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.7500. Min Act: -0.1700
Data Index: 4009175 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.5625. Min Act: -0.1700
Data Index: 5734043 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.4062. Min Act: -0.1700
Data Index: 6470317 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.4375. Min Act: -0.1700
Data Index: 4173035 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.4375. Min Act: -0.1700
Data Index: 2508411 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.3125. Min Act: -0.1700
Data Index: 7637311 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.2812. Min Act: -0.1700
Data Index: 5043974 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.2500. Min Act: -0.1700
Data Index: 844940 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.2187. Min Act: -0.1700
Data Index: 6293258 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1562. Min Act: -0.1700
Data Index: 1876629 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1875. Min Act: -0.1700
Data Index: 3150677 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1562. Min Act: -0.1700
Data Index: 6014400 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1875. Min Act: -0.1700
Data Index: 775587 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1562. Min Act: -0.1700
Data Index: 825942 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1562. Min Act: -0.1700
Data Index: 1312075 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.1250. Min Act: -0.1700
Data Index: 4721987 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.0937. Min Act: -0.1700
Data Index: 7543233 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.0937. Min Act: -0.1700
Data Index: 8182446 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9062. Min Range: -7.9062
Max Act: 7.0937. Min Act: -0.1700
Data Index: 6613687 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19