Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0053. Min Range: -8.0053
Max Act: 8.0053. Min Act: -0.1700
Data Index: 4491987 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0053. Min Range: -8.0053
Max Act: 7.6303. Min Act: -0.1700
Data Index: 4860594 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0053. Min Range: -8.0053
Max Act: 7.0365. Min Act: -0.1700
Data Index: 2577172 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0053. Min Range: -8.0053
Max Act: 7.0053. Min Act: -0.1700
Data Index: 3830755 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.9740. Min Act: -0.1700
Data Index: 4787520 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.9115. Min Act: -0.1700
Data Index: 5623348 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.8803. Min Act: -0.1700
Data Index: 4687809 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.8490. Min Act: -0.1700
Data Index: 7776080 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.8178. Min Act: -0.1700
Data Index: 1080568 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.7553. Min Act: -0.1700
Data Index: 855240 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.7553. Min Act: -0.1700
Data Index: 2462263 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.7553. Min Act: -0.1700
Data Index: 7911903 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.7240. Min Act: -0.1700
Data Index: 6328474 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6615. Min Act: -0.1700
Data Index: 2620527 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4023316 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6928. Min Act: -0.1700
Data Index: 2603323 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6303. Min Act: -0.1700
Data Index: 3817289 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6303. Min Act: -0.1700
Data Index: 1082805 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6303. Min Act: -0.1700
Data Index: 2665503 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0053. Min Range: -8.0053
Max Act: 6.6303. Min Act: -0.1700
Data Index: 233223 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19