Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.8809. Min Act: -0.1700
Data Index: 547400 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.8184. Min Act: -0.1700
Data Index: 3939668 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.7559. Min Act: -0.1700
Data Index: 1977724 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.7247. Min Act: -0.1700
Data Index: 5718040 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.6309. Min Act: -0.1700
Data Index: 6777450 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.6309. Min Act: -0.1700
Data Index: 4929695 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.6309. Min Act: -0.1700
Data Index: 6902808 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.5997. Min Act: -0.1700
Data Index: 3681133 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.5997. Min Act: -0.1700
Data Index: 6821799 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.5372. Min Act: -0.1700
Data Index: 1093987 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.5059. Min Act: -0.1700
Data Index: 3273511 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.5059. Min Act: -0.1700
Data Index: 6218002 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4434. Min Act: -0.1700
Data Index: 5465327 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4434. Min Act: -0.1700
Data Index: 5028179 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4434. Min Act: -0.1700
Data Index: 4199769 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4747. Min Act: -0.1700
Data Index: 4915685 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4434. Min Act: -0.1700
Data Index: 1117196 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4122. Min Act: -0.1700
Data Index: 3407817 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4122. Min Act: -0.1700
Data Index: 574571 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8809. Min Range: -5.8809
Max Act: 5.4122. Min Act: -0.1700
Data Index: 384705 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19