Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.6635. Min Act: -0.1700
Data Index: 1152332 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.3823. Min Act: -0.1700
Data Index: 3157315 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.4135. Min Act: -0.1700
Data Index: 4271507 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.4135. Min Act: -0.1700
Data Index: 954803 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.4135. Min Act: -0.1700
Data Index: 7618431 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.3198. Min Act: -0.1700
Data Index: 8728687 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.2885. Min Act: -0.1700
Data Index: 8428195 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.2885. Min Act: -0.1700
Data Index: 5057785 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.2885. Min Act: -0.1700
Data Index: 4469864 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.2573. Min Act: -0.1700
Data Index: 652041 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.3198. Min Act: -0.1700
Data Index: 3279385 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.2573. Min Act: -0.1700
Data Index: 6899621 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1948. Min Act: -0.1700
Data Index: 8400301 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.2260. Min Act: -0.1700
Data Index: 2643117 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1948. Min Act: -0.1700
Data Index: 54835 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1635. Min Act: -0.1700
Data Index: 6764757 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1948. Min Act: -0.1700
Data Index: 7647114 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1948. Min Act: -0.1700
Data Index: 5057791 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1635. Min Act: -0.1700
Data Index: 3103017 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6635. Min Range: -6.6635
Max Act: 6.1323. Min Act: -0.1700
Data Index: 5643215 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19