Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2370 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4048. Min Range: -4.4048
Max Act: 4.4048. Min Act: -0.1700
Data Index: 4371881 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4048. Min Range: -4.4048
Max Act: 4.0610. Min Act: -0.1700
Data Index: 3877754 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4048. Min Range: -4.4048
Max Act: 4.0298. Min Act: -0.1700
Data Index: 879753 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4048. Min Range: -4.4048
Max Act: 4.0298. Min Act: -0.1700
Data Index: 8222107 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9673. Min Act: -0.1700
Data Index: 1022793 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9673. Min Act: -0.1700
Data Index: 465583 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9673. Min Act: -0.1700
Data Index: 5808124 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9673. Min Act: -0.1700
Data Index: 1168805 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9673. Min Act: -0.1700
Data Index: 4007459 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9047. Min Act: -0.1700
Data Index: 5554994 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8735. Min Act: -0.1700
Data Index: 7175506 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.9047. Min Act: -0.1700
Data Index: 5963548 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8735. Min Act: -0.1700
Data Index: 2880446 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8422. Min Act: -0.1700
Data Index: 7828216 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8266. Min Act: -0.1700
Data Index: 4992185 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8422. Min Act: -0.1700
Data Index: 2463684 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8109. Min Act: -0.1700
Data Index: 449685 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.7953. Min Act: -0.1700
Data Index: 1545022 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.7953. Min Act: -0.1700
Data Index: 488842 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4048. Min Range: -4.4048
Max Act: 3.8109. Min Act: -0.1700
Data Index: 2592211 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19