Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6335 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.5369. Min Act: -0.1700
Data Index: 6286797 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.5369. Min Act: -0.1700
Data Index: 6357351 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.3494. Min Act: -0.1700
Data Index: 3645949 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.2869. Min Act: -0.1700
Data Index: 8788162 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.2244. Min Act: -0.1700
Data Index: 4610896 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.1619. Min Act: -0.1700
Data Index: 2760948 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.1619. Min Act: -0.1700
Data Index: 4371169 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.1619. Min Act: -0.1700
Data Index: 2202372 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.1619. Min Act: -0.1700
Data Index: 3264906 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.0994. Min Act: -0.1700
Data Index: 6317745 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.0994. Min Act: -0.1700
Data Index: 6484545 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.0994. Min Act: -0.1700
Data Index: 4892953 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 4947756 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5369. Min Range: -8.5369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 1729161 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5369. Min Range: -8.5369
Max Act: 7.9744. Min Act: -0.1700
Data Index: 7575994 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5369. Min Range: -8.5369
Max Act: 7.9744. Min Act: -0.1700
Data Index: 8235954 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5369. Min Range: -8.5369
Max Act: 7.9744. Min Act: -0.1700
Data Index: 4302182 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5369. Min Range: -8.5369
Max Act: 7.9744. Min Act: -0.1700
Data Index: 7680763 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5369. Min Range: -8.5369
Max Act: 7.9119. Min Act: -0.1700
Data Index: 158487 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5369. Min Range: -8.5369
Max Act: 7.9119. Min Act: -0.1700
Data Index: 6223854 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19