Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4645 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.6475. Min Act: -0.1700
Data Index: 2616565 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.5850. Min Act: -0.1700
Data Index: 8267693 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6142592 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6005394 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.5225. Min Act: -0.1700
Data Index: 6006606 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.4288. Min Act: -0.1700
Data Index: 3300446 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.4288. Min Act: -0.1700
Data Index: 3259499 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.3975. Min Act: -0.1700
Data Index: 1929833 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.3975. Min Act: -0.1700
Data Index: 7563803 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.3663. Min Act: -0.1700
Data Index: 1561372 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.3975. Min Act: -0.1700
Data Index: 3042939 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.3038. Min Act: -0.1700
Data Index: 572432 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2725. Min Act: -0.1700
Data Index: 7145763 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2413. Min Act: -0.1700
Data Index: 5269767 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2100. Min Act: -0.1700
Data Index: 4828023 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2413. Min Act: -0.1700
Data Index: 3606952 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2100. Min Act: -0.1700
Data Index: 430184 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2100. Min Act: -0.1700
Data Index: 7697688 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2100. Min Act: -0.1700
Data Index: 3424437 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6475. Min Range: -5.6475
Max Act: 5.2100. Min Act: -0.1700
Data Index: 6251341 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19