Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.9387. Min Act: -0.1700
Data Index: 5854294 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8762. Min Act: -0.1700
Data Index: 6233416 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8762. Min Act: -0.1700
Data Index: 5186159 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8762. Min Act: -0.1700
Data Index: 3167199 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8449. Min Act: -0.1700
Data Index: 383216 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8449. Min Act: -0.1700
Data Index: 2677456 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8136. Min Act: -0.1700
Data Index: 523327 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7980. Min Act: -0.1700
Data Index: 5378241 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8449. Min Act: -0.1700
Data Index: 1179126 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8136. Min Act: -0.1700
Data Index: 1639217 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7980. Min Act: -0.1700
Data Index: 7181877 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7823. Min Act: -0.1700
Data Index: 7879944 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 6132182 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 3738469 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 330041 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7354. Min Act: -0.1700
Data Index: 1623498 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7354. Min Act: -0.1700
Data Index: 8063315 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7354. Min Act: -0.1700
Data Index: 6692397 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7198. Min Act: -0.1700
Data Index: 2175532 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7198. Min Act: -0.1700
Data Index: 2605103 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19