Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.9542. Min Act: -0.1692
Data Index: 457020 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.9229. Min Act: -0.1700
Data Index: 3697407 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4528282 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8604. Min Act: -0.1700
Data Index: 3256452 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8604. Min Act: -0.1699
Data Index: 4675157 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8604. Min Act: -0.1700
Data Index: 8064924 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8604. Min Act: -0.1700
Data Index: 7713934 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1693
Data Index: 854213 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4163037 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1697
Data Index: 4083554 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 773387 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4083551 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 3282605 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.7979. Min Act: -0.1700
Data Index: 8642740 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4863009 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.7979. Min Act: -0.1700
Data Index: 892504 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 5701658 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1565196 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 4083553 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9542. Min Range: -5.9542
Max Act: 5.7979. Min Act: -0.1700
Data Index: 5477223 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19