Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0922. Min Range: -5.0922
Max Act: 5.0609. Min Act: -0.1700
Data Index: 1163202 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0922. Min Range: -5.0922
Max Act: 5.0922. Min Act: -0.1700
Data Index: 6112667 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0922. Min Range: -5.0922
Max Act: 5.0609. Min Act: -0.1700
Data Index: 405064 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.9984. Min Act: -0.1700
Data Index: 8598961 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.9672. Min Act: -0.1700
Data Index: 2170321 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.9047. Min Act: -0.1700
Data Index: 6267408 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8734. Min Act: -0.1700
Data Index: 7894130 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8734. Min Act: -0.1700
Data Index: 4390557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8734. Min Act: -0.1700
Data Index: 1523777 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8734. Min Act: -0.1700
Data Index: 8801077 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8734. Min Act: -0.1700
Data Index: 6799442 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8422. Min Act: -0.1700
Data Index: 2527133 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8422. Min Act: -0.1700
Data Index: 405065 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8422. Min Act: -0.1700
Data Index: 6070726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8109. Min Act: -0.1700
Data Index: 2957164 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.7797. Min Act: -0.1700
Data Index: 1098378 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8109. Min Act: -0.1700
Data Index: 754516 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.8109. Min Act: -0.1700
Data Index: 2110879 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.7797. Min Act: -0.1700
Data Index: 2815861 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0922. Min Range: -5.0922
Max Act: 4.7484. Min Act: -0.1700
Data Index: 7264102 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19