Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.6738. Min Act: -0.1700
Data Index: 4093147 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.6113. Min Act: -0.1700
Data Index: 7450623 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.5488. Min Act: -0.1700
Data Index: 2166305 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.4238. Min Act: -0.1700
Data Index: 3011065 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.3925. Min Act: -0.1700
Data Index: 3011064 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.3300. Min Act: -0.1700
Data Index: 7258295 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4778989 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.2675. Min Act: -0.1700
Data Index: 6821906 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.2363. Min Act: -0.1700
Data Index: 8580107 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.2363. Min Act: -0.1700
Data Index: 2855705 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.1738. Min Act: -0.1700
Data Index: 7807312 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.1425. Min Act: -0.1700
Data Index: 6925577 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.1113. Min Act: -0.1700
Data Index: 3484165 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.1113. Min Act: -0.1700
Data Index: 3644042 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.1113. Min Act: -0.1700
Data Index: 3472398 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.0488. Min Act: -0.1700
Data Index: 8425026 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.0488. Min Act: -0.1700
Data Index: 1953144 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.0175. Min Act: -0.1700
Data Index: 2587850 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6738. Min Range: -6.6738
Max Act: 6.0175. Min Act: -0.1700
Data Index: 3942259 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6738. Min Range: -6.6738
Max Act: 5.9863. Min Act: -0.1700
Data Index: 1400211 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19