Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.2559. Min Act: -0.1700
Data Index: 8256914 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.1621. Min Act: -0.1700
Data Index: 1383377 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.1621. Min Act: -0.1700
Data Index: 8256911 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3106188 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.0996. Min Act: -0.1700
Data Index: 2581088 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.0059. Min Act: -0.1700
Data Index: 1291712 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.0371. Min Act: -0.1700
Data Index: 3389514 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2559. Min Range: -5.2559
Max Act: 5.0059. Min Act: -0.1700
Data Index: 615688 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9746. Min Act: -0.1700
Data Index: 2510027 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9746. Min Act: -0.1700
Data Index: 6146447 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9434. Min Act: -0.1700
Data Index: 4216689 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9434. Min Act: -0.1700
Data Index: 6478533 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6433253 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8256915 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6781402 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6811927 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.8496. Min Act: -0.1700
Data Index: 339902 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6752021 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.9121. Min Act: -0.1700
Data Index: 737227 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2559. Min Range: -5.2559
Max Act: 4.8809. Min Act: -0.1700
Data Index: 2944916 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19