Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0081. Min Range: -4.0081
Max Act: 4.0081. Min Act: -0.1700
Data Index: 3543131 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8830. Min Act: -0.1700
Data Index: 2119389 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.9143. Min Act: -0.1700
Data Index: 8626220 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.9143. Min Act: -0.1700
Data Index: 76049 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8830. Min Act: -0.1700
Data Index: 230464 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8830. Min Act: -0.1700
Data Index: 1481410 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8830. Min Act: -0.1700
Data Index: 4624086 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8830. Min Act: -0.1700
Data Index: 8080890 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8830. Min Act: -0.1700
Data Index: 3734147 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8674. Min Act: -0.1700
Data Index: 7035117 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8674. Min Act: -0.1700
Data Index: 344131 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8674. Min Act: -0.1700
Data Index: 2111158 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8674. Min Act: -0.1700
Data Index: 6993772 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8517. Min Act: -0.1700
Data Index: 7895655 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8361. Min Act: -0.1700
Data Index: 5755833 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8361. Min Act: -0.1700
Data Index: 6955562 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8361. Min Act: -0.1700
Data Index: 1370259 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8048. Min Act: -0.1700
Data Index: 262150 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8048. Min Act: -0.1700
Data Index: 2587634 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0081. Min Range: -4.0081
Max Act: 3.8048. Min Act: -0.1700
Data Index: 3536826 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19