Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.9175. Min Act: -0.1700
Data Index: 8497778 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.8550. Min Act: -0.1700
Data Index: 4553931 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7940420 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7925. Min Act: -0.1700
Data Index: 953721 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5276322 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5572405 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7300. Min Act: -0.1700
Data Index: 3732528 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7300. Min Act: -0.1700
Data Index: 854393 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.7300. Min Act: -0.1700
Data Index: 4553934 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6988. Min Act: -0.1700
Data Index: 7956933 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6988. Min Act: -0.1700
Data Index: 7543537 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6988. Min Act: -0.1700
Data Index: 5322474 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6988. Min Act: -0.1700
Data Index: 7433053 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6675. Min Act: -0.1700
Data Index: 8607676 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6675. Min Act: -0.1700
Data Index: 4956430 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6675. Min Act: -0.1700
Data Index: 2449734 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6675. Min Act: -0.1700
Data Index: 7768738 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6675. Min Act: -0.1700
Data Index: 6534734 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6363. Min Act: -0.1700
Data Index: 2229697 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9175. Min Range: -5.9175
Max Act: 5.6363. Min Act: -0.1700
Data Index: 361830 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19