Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2093 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 1584271 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.5094. Min Act: -0.1700
Data Index: 7136664 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.4782. Min Act: -0.1700
Data Index: 7237750 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.4157. Min Act: -0.1700
Data Index: 4619488 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.4157. Min Act: -0.1700
Data Index: 5124295 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.4157. Min Act: -0.1700
Data Index: 4900311 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.3844. Min Act: -0.1700
Data Index: 2791342 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.3532. Min Act: -0.1700
Data Index: 3234456 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.3219. Min Act: -0.1700
Data Index: 7279098 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2907. Min Act: -0.1700
Data Index: 5333926 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2907. Min Act: -0.1700
Data Index: 426037 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2907. Min Act: -0.1700
Data Index: 8182976 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2907. Min Act: -0.1700
Data Index: 5221325 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2907. Min Act: -0.1700
Data Index: 6341078 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2594. Min Act: -0.1700
Data Index: 7669038 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2594. Min Act: -0.1700
Data Index: 2676347 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2594. Min Act: -0.1700
Data Index: 3681990 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2594. Min Act: -0.1700
Data Index: 7702447 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2594. Min Act: -0.1700
Data Index: 5169541 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5094. Min Range: -4.5094
Max Act: 4.2282. Min Act: -0.1700
Data Index: 3070274 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19