Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.6857. Min Act: -0.1700
Data Index: 4744456 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.6232. Min Act: -0.1700
Data Index: 4155886 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.5294. Min Act: -0.1700
Data Index: 7065679 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.5294. Min Act: -0.1700
Data Index: 6643268 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.5294. Min Act: -0.1700
Data Index: 6637961 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4982. Min Act: -0.1700
Data Index: 4051811 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4669. Min Act: -0.1700
Data Index: 7786879 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4669. Min Act: -0.1700
Data Index: 5821561 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4669. Min Act: -0.1700
Data Index: 8350306 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4669. Min Act: -0.1700
Data Index: 6983149 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4357. Min Act: -0.1700
Data Index: 5751530 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4044. Min Act: -0.1700
Data Index: 8509213 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4044. Min Act: -0.1700
Data Index: 5316124 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.3732. Min Act: -0.1700
Data Index: 5105786 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.4044. Min Act: -0.1700
Data Index: 8696398 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.3419. Min Act: -0.1700
Data Index: 512272 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.3419. Min Act: -0.1700
Data Index: 5627476 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.3107. Min Act: -0.1700
Data Index: 8590796 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.3732. Min Act: -0.1700
Data Index: 3846797 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6857. Min Range: -5.6857
Max Act: 5.3107. Min Act: -0.1700
Data Index: 4719749 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19