Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3744 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5811. Min Range: -6.5811
Max Act: 6.5811. Min Act: -0.1700
Data Index: 334993 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5811. Min Range: -6.5811
Max Act: 6.3936. Min Act: -0.1700
Data Index: 7659720 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5811. Min Range: -6.5811
Max Act: 6.1749. Min Act: -0.1700
Data Index: 6520957 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5811. Min Range: -6.5811
Max Act: 6.0811. Min Act: -0.1700
Data Index: 350918 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.9561. Min Act: -0.1700
Data Index: 8070307 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.9874. Min Act: -0.1700
Data Index: 3216525 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.9249. Min Act: -0.1700
Data Index: 2428586 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3872351 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7686. Min Act: -0.1700
Data Index: 3499503 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7999. Min Act: -0.1700
Data Index: 6623206 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7999. Min Act: -0.1700
Data Index: 3208230 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7686. Min Act: -0.1700
Data Index: 1793424 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7999. Min Act: -0.1700
Data Index: 169575 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7061. Min Act: -0.1700
Data Index: 8424848 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.6436. Min Act: -0.1700
Data Index: 3980461 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.6749. Min Act: -0.1700
Data Index: 6128985 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.6436. Min Act: -0.1700
Data Index: 896607 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7061. Min Act: -0.1700
Data Index: 8154563 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.6749. Min Act: -0.1700
Data Index: 7206685 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5811. Min Range: -6.5811
Max Act: 5.7061. Min Act: -0.1700
Data Index: 4865592 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19