Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1558 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0243. Min Range: -5.0243
Max Act: 5.0243. Min Act: -0.1700
Data Index: 8285824 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8680. Min Act: -0.1700
Data Index: 2245317 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8680. Min Act: -0.1700
Data Index: 629322 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8368. Min Act: -0.1700
Data Index: 4671931 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8680. Min Act: -0.1700
Data Index: 1606622 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8680. Min Act: -0.1700
Data Index: 1716129 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8368. Min Act: -0.1700
Data Index: 8418956 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8055. Min Act: -0.1700
Data Index: 8639336 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8055. Min Act: -0.1700
Data Index: 6737670 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5446423 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7743. Min Act: -0.1700
Data Index: 7701457 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7430. Min Act: -0.1700
Data Index: 2937630 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7118. Min Act: -0.1700
Data Index: 4341014 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7118. Min Act: -0.1700
Data Index: 2384599 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7430. Min Act: -0.1700
Data Index: 227954 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7118. Min Act: -0.1700
Data Index: 377507 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7118. Min Act: -0.1700
Data Index: 306133 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.7118. Min Act: -0.1700
Data Index: 5002738 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.6493. Min Act: -0.1700
Data Index: 3569053 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0243. Min Range: -5.0243
Max Act: 4.6805. Min Act: -0.1700
Data Index: 600108 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19