Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.6010. Min Act: -0.1700
Data Index: 579345 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.4135. Min Act: -0.1700
Data Index: 4562858 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.3510. Min Act: -0.1700
Data Index: 3505216 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.2885. Min Act: -0.1700
Data Index: 2744191 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.2260. Min Act: -0.1700
Data Index: 2294482 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.2260. Min Act: -0.1700
Data Index: 6361053 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.2260. Min Act: -0.1700
Data Index: 6428169 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.2260. Min Act: -0.1700
Data Index: 7248941 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4022326 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4769096 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1635. Min Act: -0.1700
Data Index: 5087909 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1635. Min Act: -0.1700
Data Index: 5171967 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4039711 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1323. Min Act: -0.1700
Data Index: 3723624 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1323. Min Act: -0.1700
Data Index: 4811528 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1323. Min Act: -0.1700
Data Index: 5770874 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1323. Min Act: -0.1699
Data Index: 8060399 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1010. Min Act: -0.1700
Data Index: 5996642 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1010. Min Act: -0.1700
Data Index: 4563257 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6010. Min Range: -6.6010
Max Act: 6.1010. Min Act: -0.1700
Data Index: 2837905 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19