Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0406. Min Range: -7.0406
Max Act: 7.0406. Min Act: -0.1700
Data Index: 6055900 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0406. Min Range: -7.0406
Max Act: 7.0406. Min Act: -0.1700
Data Index: 2941100 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0406. Min Range: -7.0406
Max Act: 7.0094. Min Act: -0.1700
Data Index: 7444871 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.9781. Min Act: -0.1700
Data Index: 1211867 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.9469. Min Act: -0.1700
Data Index: 5824588 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8844. Min Act: -0.1700
Data Index: 3353846 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8844. Min Act: -0.1700
Data Index: 8803831 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8531. Min Act: -0.1700
Data Index: 4294344 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8219. Min Act: -0.1700
Data Index: 862564 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8219. Min Act: -0.1700
Data Index: 3841751 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8219. Min Act: -0.1700
Data Index: 4034466 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.7906. Min Act: -0.1700
Data Index: 4045304 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8219. Min Act: -0.1700
Data Index: 5597343 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.7906. Min Act: -0.1700
Data Index: 4019231 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8219. Min Act: -0.1700
Data Index: 8706583 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.8219. Min Act: -0.1700
Data Index: 7807997 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.7594. Min Act: -0.1700
Data Index: 3703263 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.7906. Min Act: -0.1700
Data Index: 1646979 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.7906. Min Act: -0.1700
Data Index: 7179222 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0406. Min Range: -7.0406
Max Act: 6.7906. Min Act: -0.1700
Data Index: 2963289 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19