Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.5544. Min Act: -0.1700
Data Index: 3496582 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.4919. Min Act: -0.1700
Data Index: 498217 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.3981. Min Act: -0.1700
Data Index: 3677824 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.3669. Min Act: -0.1700
Data Index: 5234513 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.3044. Min Act: -0.1700
Data Index: 6085018 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.2419. Min Act: -0.1700
Data Index: 651073 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.2419. Min Act: -0.1700
Data Index: 3512034 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.2106. Min Act: -0.1700
Data Index: 3536379 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.2106. Min Act: -0.1700
Data Index: 1580955 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.2106. Min Act: -0.1700
Data Index: 4342228 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.2106. Min Act: -0.1700
Data Index: 8329700 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.1794. Min Act: -0.1700
Data Index: 579968 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.1481. Min Act: -0.1700
Data Index: 8392749 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.1481. Min Act: -0.1700
Data Index: 6799138 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.1481. Min Act: -0.1700
Data Index: 4777071 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.1481. Min Act: -0.1700
Data Index: 5848052 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.0856. Min Act: -0.1700
Data Index: 7299100 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.1169. Min Act: -0.1700
Data Index: 2648851 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.0856. Min Act: -0.1700
Data Index: 6312548 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5544. Min Range: -5.5544
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3951031 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19