Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4394. Min Range: -8.4394
Max Act: 8.4394. Min Act: -0.1700
Data Index: 6822615 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4394. Min Range: -8.4394
Max Act: 8.1269. Min Act: -0.1700
Data Index: 5201777 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4394. Min Range: -8.4394
Max Act: 8.1269. Min Act: -0.1700
Data Index: 3444296 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4394. Min Range: -8.4394
Max Act: 8.0019. Min Act: -0.1700
Data Index: 3239855 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4394. Min Range: -8.4394
Max Act: 8.0019. Min Act: -0.1700
Data Index: 2161617 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9707. Min Act: -0.1700
Data Index: 789157 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9707. Min Act: -0.1700
Data Index: 4661469 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9707. Min Act: -0.1700
Data Index: 1781179 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9394. Min Act: -0.1700
Data Index: 8095855 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9394. Min Act: -0.1700
Data Index: 5127552 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9394. Min Act: -0.1700
Data Index: 6582450 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9394. Min Act: -0.1700
Data Index: 4661470 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9394. Min Act: -0.1700
Data Index: 6050249 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.8769. Min Act: -0.1700
Data Index: 7062972 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.9082. Min Act: -0.1700
Data Index: 4670085 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.8769. Min Act: -0.1700
Data Index: 3951596 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.8769. Min Act: -0.1700
Data Index: 5867672 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.8457. Min Act: -0.1700
Data Index: 1650534 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.8457. Min Act: -0.1700
Data Index: 6755064 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4394. Min Range: -8.4394
Max Act: 7.8144. Min Act: -0.1700
Data Index: 8707809 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19