Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4391637 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6641. Min Act: -0.1700
Data Index: 7732402 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6016. Min Act: -0.1700
Data Index: 2149743 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.4766. Min Act: -0.1700
Data Index: 4871890 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.4766. Min Act: -0.1700
Data Index: 7070449 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.4453. Min Act: -0.1700
Data Index: 447007 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.3828. Min Act: -0.1700
Data Index: 2906362 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.3516. Min Act: -0.1700
Data Index: 6328726 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.3203. Min Act: -0.1700
Data Index: 5349384 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2891. Min Act: -0.1700
Data Index: 3500793 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.3516. Min Act: -0.1700
Data Index: 7365051 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2578. Min Act: -0.1700
Data Index: 5545442 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2891. Min Act: -0.1700
Data Index: 7543485 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2891. Min Act: -0.1700
Data Index: 2179708 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2891. Min Act: -0.1700
Data Index: 6583405 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2891. Min Act: -0.1700
Data Index: 2923128 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2578. Min Act: -0.1700
Data Index: 8124176 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2578. Min Act: -0.1700
Data Index: 3270389 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2266. Min Act: -0.1700
Data Index: 5781585 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.2891. Min Act: -0.1700
Data Index: 6584551 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19