Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.4583. Min Act: -0.1700
Data Index: 3918357 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.4271. Min Act: -0.1700
Data Index: 4083200 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.3333. Min Act: -0.1700
Data Index: 6026055 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.2708. Min Act: -0.1700
Data Index: 2479562 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.1146. Min Act: -0.1700
Data Index: 3559134 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.0521. Min Act: -0.1700
Data Index: 7014482 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.0521. Min Act: -0.1700
Data Index: 92476 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.0208. Min Act: -0.1700
Data Index: 2723141 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.9896. Min Act: -0.1700
Data Index: 1870848 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4583. Min Range: -7.4583
Max Act: 7.0208. Min Act: -0.1700
Data Index: 4222435 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.9583. Min Act: -0.1700
Data Index: 8165292 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8646. Min Act: -0.1700
Data Index: 2570383 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8333. Min Act: -0.1700
Data Index: 5828343 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8646. Min Act: -0.1700
Data Index: 8633834 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8646. Min Act: -0.1700
Data Index: 7644723 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8333. Min Act: -0.1700
Data Index: 3669398 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8333. Min Act: -0.1700
Data Index: 1537165 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8021. Min Act: -0.1700
Data Index: 5260659 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8021. Min Act: -0.1700
Data Index: 3686974 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4583. Min Range: -7.4583
Max Act: 6.8021. Min Act: -0.1700
Data Index: 4537393 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19