Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.3257. Min Act: -0.1700
Data Index: 970219 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.3257. Min Act: -0.1700
Data Index: 3085250 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.2632. Min Act: -0.1700
Data Index: 7104811 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.1069. Min Act: -0.1700
Data Index: 1121760 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.1069. Min Act: -0.1700
Data Index: 4637007 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0757. Min Act: -0.1700
Data Index: 3625370 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0757. Min Act: -0.1700
Data Index: 3433220 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0444. Min Act: -0.1700
Data Index: 3124248 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0132. Min Act: -0.1700
Data Index: 6857766 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0132. Min Act: -0.1700
Data Index: 8336023 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0444. Min Act: -0.1700
Data Index: 8246390 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3257. Min Range: -7.3257
Max Act: 7.0757. Min Act: -0.1700
Data Index: 5392892 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9819. Min Act: -0.1700
Data Index: 6120416 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9819. Min Act: -0.1700
Data Index: 6767900 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9819. Min Act: -0.1700
Data Index: 2747612 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9507. Min Act: -0.1700
Data Index: 2096956 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9194. Min Act: -0.1700
Data Index: 7548747 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9194. Min Act: -0.1700
Data Index: 1362928 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9194. Min Act: -0.1700
Data Index: 6768999 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3257. Min Range: -7.3257
Max Act: 6.9194. Min Act: -0.1700
Data Index: 36309 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19