Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0249. Min Range: -2.0249
Max Act: 2.0249. Min Act: -0.1700
Data Index: 4636168 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0249. Min Range: -2.0249
Max Act: 2.0080. Min Act: -0.1700
Data Index: 2337188 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9911. Min Act: -0.1700
Data Index: 4636167 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9573. Min Act: -0.1700
Data Index: 5021169 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9573. Min Act: -0.1700
Data Index: 3907211 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9573. Min Act: -0.1700
Data Index: 5143516 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9573. Min Act: -0.1700
Data Index: 1537710 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9233. Min Act: -0.1700
Data Index: 4635321 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9403. Min Act: -0.1700
Data Index: 2888205 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9403. Min Act: -0.1700
Data Index: 3373432 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9233. Min Act: -0.1700
Data Index: 8443832 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9233. Min Act: -0.1700
Data Index: 5697502 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9233. Min Act: -0.1700
Data Index: 4019861 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9062. Min Act: -0.1700
Data Index: 3042604 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9233. Min Act: -0.1700
Data Index: 1027061 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9233. Min Act: -0.1700
Data Index: 3723570 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.8892. Min Act: -0.1700
Data Index: 1112884 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9062. Min Act: -0.1698
Data Index: 3385004 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9062. Min Act: -0.1700
Data Index: 5498385 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0249. Min Range: -2.0249
Max Act: 1.9062. Min Act: -0.1700
Data Index: 559522 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19