Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0809. Min Range: -4.0809
Max Act: 4.0809. Min Act: -0.1700
Data Index: 5668883 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0809. Min Range: -4.0809
Max Act: 4.0809. Min Act: -0.1700
Data Index: 2928945 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0809. Min Range: -4.0809
Max Act: 4.0183. Min Act: -0.1700
Data Index: 3370139 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0809. Min Range: -4.0809
Max Act: 4.0496. Min Act: -0.1700
Data Index: 3370141 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9871. Min Act: -0.1700
Data Index: 6832503 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0809. Min Range: -4.0809
Max Act: 4.0183. Min Act: -0.1700
Data Index: 7709907 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9871. Min Act: -0.1700
Data Index: 6142404 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0809. Min Range: -4.0809
Max Act: 4.0183. Min Act: -0.1700
Data Index: 8297250 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9558. Min Act: -0.1700
Data Index: 2146096 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9558. Min Act: -0.1700
Data Index: 2972158 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9871. Min Act: -0.1700
Data Index: 808460 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9558. Min Act: -0.1700
Data Index: 7375134 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9558. Min Act: -0.1700
Data Index: 973616 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9558. Min Act: -0.1700
Data Index: 8230873 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.8933. Min Act: -0.1700
Data Index: 2400139 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.9558. Min Act: -0.1700
Data Index: 1964013 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.8933. Min Act: -0.1700
Data Index: 4925384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.8933. Min Act: -0.1700
Data Index: 1000760 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.8933. Min Act: -0.1700
Data Index: 4092563 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0809. Min Range: -4.0809
Max Act: 3.8620. Min Act: -0.1700
Data Index: 2129266 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19