Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2754. Min Range: -7.2754
Max Act: 7.2754. Min Act: -0.1700
Data Index: 179606 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2754. Min Range: -7.2754
Max Act: 7.2129. Min Act: -0.1700
Data Index: 6976006 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2754. Min Range: -7.2754
Max Act: 7.1816. Min Act: -0.1700
Data Index: 4149482 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2754. Min Range: -7.2754
Max Act: 7.0254. Min Act: -0.1700
Data Index: 6099381 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.9941. Min Act: -0.1700
Data Index: 5179193 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.9316. Min Act: -0.1700
Data Index: 3258616 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.9004. Min Act: -0.1700
Data Index: 6766539 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.8691. Min Act: -0.1700
Data Index: 3357248 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.8066. Min Act: -0.1700
Data Index: 5568354 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.8066. Min Act: -0.1700
Data Index: 8300059 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.8066. Min Act: -0.1700
Data Index: 8010752 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.8066. Min Act: -0.1700
Data Index: 3695887 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.7754. Min Act: -0.1700
Data Index: 5681808 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1453133 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.7441. Min Act: -0.1700
Data Index: 8200963 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.7441. Min Act: -0.1700
Data Index: 6379762 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1841140 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.7129. Min Act: -0.1700
Data Index: 8664089 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.6816. Min Act: -0.1700
Data Index: 6705094 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2754. Min Range: -7.2754
Max Act: 6.6816. Min Act: -0.1700
Data Index: 2848710 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19