Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2341. Min Range: -5.2341
Max Act: 5.2341. Min Act: -0.1700
Data Index: 148015 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2341. Min Range: -5.2341
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1127966 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2341. Min Range: -5.2341
Max Act: 5.1404. Min Act: -0.1700
Data Index: 7296546 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2341. Min Range: -5.2341
Max Act: 5.0779. Min Act: -0.1700
Data Index: 334158 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2341. Min Range: -5.2341
Max Act: 5.0466. Min Act: -0.1700
Data Index: 6358224 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2341. Min Range: -5.2341
Max Act: 5.0466. Min Act: -0.1700
Data Index: 6975544 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.9216. Min Act: -0.1700
Data Index: 2860120 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8904. Min Act: -0.1700
Data Index: 5074841 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8904. Min Act: -0.1700
Data Index: 2437953 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8279. Min Act: -0.1700
Data Index: 1097581 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8279. Min Act: -0.1700
Data Index: 3615430 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8279. Min Act: -0.1700
Data Index: 971226 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8279. Min Act: -0.1700
Data Index: 1602045 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.7654. Min Act: -0.1700
Data Index: 2312380 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.8279. Min Act: -0.1700
Data Index: 824507 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.7966. Min Act: -0.1700
Data Index: 6620462 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.7966. Min Act: -0.1700
Data Index: 8807235 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.7966. Min Act: -0.1700
Data Index: 1505452 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.7654. Min Act: -0.1700
Data Index: 3115594 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2341. Min Range: -5.2341
Max Act: 4.7341. Min Act: -0.1700
Data Index: 329665 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19