Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.4939. Min Act: -0.1700
Data Index: 2497665 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.3064. Min Act: -0.1700
Data Index: 3544269 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.2439. Min Act: -0.1700
Data Index: 7193582 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.2127. Min Act: -0.1700
Data Index: 7518385 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.2127. Min Act: -0.1700
Data Index: 4226856 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.1814. Min Act: -0.1700
Data Index: 7521871 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.1814. Min Act: -0.1700
Data Index: 1729278 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.1189. Min Act: -0.1700
Data Index: 2431687 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.1189. Min Act: -0.1700
Data Index: 4714631 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0877. Min Act: -0.1700
Data Index: 1502337 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0252. Min Act: -0.1700
Data Index: 2082989 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0564. Min Act: -0.1700
Data Index: 3653047 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0564. Min Act: -0.1700
Data Index: 6994943 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4939. Min Range: -5.4939
Max Act: 4.9939. Min Act: -0.1700
Data Index: 4076055 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0252. Min Act: -0.1700
Data Index: 8104308 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0252. Min Act: -0.1700
Data Index: 6666855 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0252. Min Act: -0.1700
Data Index: 1734562 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0252. Min Act: -0.1700
Data Index: 3333626 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0564. Min Act: -0.1700
Data Index: 6478370 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4939. Min Range: -5.4939
Max Act: 5.0252. Min Act: -0.1700
Data Index: 3633825 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19