Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.4854. Min Act: -0.1700
Data Index: 3593281 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.4229. Min Act: -0.1700
Data Index: 1309896 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.4229. Min Act: -0.1700
Data Index: 8461687 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.3604. Min Act: -0.1700
Data Index: 4864843 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.3292. Min Act: -0.1700
Data Index: 1283871 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.2667. Min Act: -0.1700
Data Index: 3414164 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.2667. Min Act: -0.1700
Data Index: 3814560 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.2354. Min Act: -0.1700
Data Index: 3306240 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.2042. Min Act: -0.1700
Data Index: 4766605 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.2354. Min Act: -0.1700
Data Index: 8542293 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.2042. Min Act: -0.1700
Data Index: 75433 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.1729. Min Act: -0.1700
Data Index: 1677657 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.1417. Min Act: -0.1700
Data Index: 4429233 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.1417. Min Act: -0.1700
Data Index: 311147 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.1417. Min Act: -0.1700
Data Index: 6223528 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.1417. Min Act: -0.1700
Data Index: 8753548 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.1104. Min Act: -0.1700
Data Index: 6529322 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.0792. Min Act: -0.1700
Data Index: 3904902 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.0792. Min Act: -0.1698
Data Index: 6600819 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4854. Min Range: -5.4854
Max Act: 5.0479. Min Act: -0.1700
Data Index: 4937353 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19