Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.8983. Min Act: -0.1700
Data Index: 5481414 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.6170. Min Act: -0.1700
Data Index: 4900350 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.6483. Min Act: -0.1700
Data Index: 1802595 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.5858. Min Act: -0.1700
Data Index: 4510982 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.5858. Min Act: -0.1700
Data Index: 517271 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.5545. Min Act: -0.1700
Data Index: 3747598 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.5545. Min Act: -0.1700
Data Index: 2691237 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4920. Min Act: -0.1700
Data Index: 7014731 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4920. Min Act: -0.1700
Data Index: 7631343 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4920. Min Act: -0.1700
Data Index: 5686245 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4608. Min Act: -0.1700
Data Index: 4255573 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4608. Min Act: -0.1700
Data Index: 1063614 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4608. Min Act: -0.1700
Data Index: 2607850 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4295. Min Act: -0.1700
Data Index: 764594 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4295. Min Act: -0.1700
Data Index: 6819231 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4295. Min Act: -0.1700
Data Index: 2607854 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.3983. Min Act: -0.1700
Data Index: 4531639 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.4295. Min Act: -0.1700
Data Index: 5275241 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.3983. Min Act: -0.1700
Data Index: 6449000 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8983. Min Range: -4.8983
Max Act: 4.3983. Min Act: -0.1700
Data Index: 7714066 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19