Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.8022. Min Act: -0.1700
Data Index: 8618478 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.3022. Min Act: -0.1700
Data Index: 3618629 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.2397. Min Act: -0.1700
Data Index: 3289306 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.1772. Min Act: -0.1700
Data Index: 5759448 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.1147. Min Act: -0.1700
Data Index: 7986105 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.1147. Min Act: -0.1700
Data Index: 3959181 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8022. Min Range: -9.8022
Max Act: 9.0522. Min Act: -0.1700
Data Index: 9038 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9897. Min Act: -0.1700
Data Index: 6996294 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9897. Min Act: -0.1700
Data Index: 5061057 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9272. Min Act: -0.1700
Data Index: 2735946 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9897. Min Act: -0.1700
Data Index: 7465648 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9897. Min Act: -0.1700
Data Index: 440660 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9897. Min Act: -0.1700
Data Index: 4047680 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9272. Min Act: -0.1700
Data Index: 8154892 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9272. Min Act: -0.1700
Data Index: 3566802 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9272. Min Act: -0.1700
Data Index: 1732254 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9272. Min Act: -0.1700
Data Index: 5664781 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9272. Min Act: -0.1700
Data Index: 4333515 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.9897. Min Act: -0.1700
Data Index: 2328383 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8022. Min Range: -9.8022
Max Act: 8.8647. Min Act: -0.1700
Data Index: 6011468 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19