Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0510. Min Range: -5.0510
Max Act: 5.0510. Min Act: -0.1700
Data Index: 921436 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.9573. Min Act: -0.1700
Data Index: 6596655 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.9885. Min Act: -0.1700
Data Index: 4265821 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.8635. Min Act: -0.1700
Data Index: 3871271 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.8323. Min Act: -0.1700
Data Index: 3425345 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.8323. Min Act: -0.1700
Data Index: 3518086 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.8010. Min Act: -0.1700
Data Index: 5116494 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.7698. Min Act: -0.1700
Data Index: 3932054 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.7385. Min Act: -0.1700
Data Index: 4025506 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.7385. Min Act: -0.1700
Data Index: 7594691 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.7385. Min Act: -0.1700
Data Index: 2024787 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.7073. Min Act: -0.1700
Data Index: 5506685 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.7073. Min Act: -0.1700
Data Index: 1762701 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6760. Min Act: -0.1700
Data Index: 5246087 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6760. Min Act: -0.1700
Data Index: 689784 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6760. Min Act: -0.1700
Data Index: 3406848 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6448. Min Act: -0.1700
Data Index: 4327975 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6448. Min Act: -0.1700
Data Index: 506863 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6135. Min Act: -0.1700
Data Index: 8684884 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0510. Min Range: -5.0510
Max Act: 4.6135. Min Act: -0.1700
Data Index: 5008473 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19