Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6932. Min Act: -0.1700
Data Index: 6633796 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6932. Min Act: -0.1700
Data Index: 3896615 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6619. Min Act: -0.1700
Data Index: 5573122 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6619. Min Act: -0.1700
Data Index: 8567602 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6307. Min Act: -0.1700
Data Index: 2299347 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6619. Min Act: -0.1700
Data Index: 3502520 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6307. Min Act: -0.1700
Data Index: 7679935 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6307. Min Act: -0.1700
Data Index: 8290918 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.6307. Min Act: -0.1700
Data Index: 1675249 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5994. Min Act: -0.1700
Data Index: 1909672 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5994. Min Act: -0.1700
Data Index: 8632510 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 6707635 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5369. Min Act: -0.1700
Data Index: 2313861 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 3735610 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5057. Min Act: -0.1700
Data Index: 652315 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 384304 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 2895003 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 4102012 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 38032 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6932. Min Range: -4.6932
Max Act: 4.5682. Min Act: -0.1700
Data Index: 5133636 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19