Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3744 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5397. Min Range: -8.5397
Max Act: 8.5397. Min Act: -0.1700
Data Index: 2212359 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5397. Min Range: -8.5397
Max Act: 8.4772. Min Act: -0.1700
Data Index: 2818229 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5397. Min Range: -8.5397
Max Act: 8.3522. Min Act: -0.1700
Data Index: 2995728 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5397. Min Range: -8.5397
Max Act: 8.2897. Min Act: -0.1700
Data Index: 579261 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5397. Min Range: -8.5397
Max Act: 8.1960. Min Act: -0.1700
Data Index: 3049466 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5397. Min Range: -8.5397
Max Act: 8.1335. Min Act: -0.1700
Data Index: 1391071 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.9147. Min Act: -0.1700
Data Index: 1194834 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.8835. Min Act: -0.1700
Data Index: 6251454 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.8522. Min Act: -0.1700
Data Index: 5490976 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.8522. Min Act: -0.1700
Data Index: 3091962 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.8522. Min Act: -0.1700
Data Index: 2612455 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.8210. Min Act: -0.1700
Data Index: 2442368 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.8210. Min Act: -0.1700
Data Index: 850915 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.7585. Min Act: -0.1700
Data Index: 8759490 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.7272. Min Act: -0.1700
Data Index: 2442367 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.6647. Min Act: -0.1700
Data Index: 4164100 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.6647. Min Act: -0.1700
Data Index: 6908089 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.6022. Min Act: -0.1700
Data Index: 4530387 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.6335. Min Act: -0.1700
Data Index: 4324594 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5397. Min Range: -8.5397
Max Act: 7.6335. Min Act: -0.1700
Data Index: 5525412 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19