Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1573 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.4888. Min Act: -0.1700
Data Index: 940137 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.4263. Min Act: -0.1700
Data Index: 8508353 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.3638. Min Act: -0.1700
Data Index: 2452854 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2701. Min Act: -0.1700
Data Index: 6153542 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2388. Min Act: -0.1700
Data Index: 722635 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2076. Min Act: -0.1700
Data Index: 2893264 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2388. Min Act: -0.1700
Data Index: 6267153 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.2076. Min Act: -0.1700
Data Index: 1352928 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1763. Min Act: -0.1700
Data Index: 3272422 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1451. Min Act: -0.1700
Data Index: 1447425 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1763. Min Act: -0.1700
Data Index: 7054078 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1763. Min Act: -0.1700
Data Index: 3268983 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1451. Min Act: -0.1700
Data Index: 3110958 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1763. Min Act: -0.1700
Data Index: 7729399 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1451. Min Act: -0.1700
Data Index: 4870619 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1763. Min Act: -0.1700
Data Index: 3350572 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1138. Min Act: -0.1700
Data Index: 4838486 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1138. Min Act: -0.1700
Data Index: 17384 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1138. Min Act: -0.1700
Data Index: 5811366 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4888. Min Range: -5.4888
Max Act: 5.1138. Min Act: -0.1700
Data Index: 3224646 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19