Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1672. Min Range: -6.1672
Max Act: 6.1672. Min Act: -0.1700
Data Index: 4350277 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1672. Min Range: -6.1672
Max Act: 6.0109. Min Act: -0.1700
Data Index: 995056 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.9484. Min Act: -0.1700
Data Index: 4272067 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.9484. Min Act: -0.1700
Data Index: 6878486 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.9484. Min Act: -0.1700
Data Index: 5655559 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.9484. Min Act: -0.1700
Data Index: 4907940 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.8859. Min Act: -0.1700
Data Index: 8080511 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.8859. Min Act: -0.1700
Data Index: 5789518 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.9172. Min Act: -0.1700
Data Index: 4605123 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.7609. Min Act: -0.1700
Data Index: 1322149 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.7922. Min Act: -0.1700
Data Index: 634154 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.7297. Min Act: -0.1700
Data Index: 2702151 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.7609. Min Act: -0.1700
Data Index: 411600 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.6984. Min Act: -0.1700
Data Index: 7777296 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.6359. Min Act: -0.1700
Data Index: 8083545 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.6672. Min Act: -0.1700
Data Index: 8248151 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.6047. Min Act: -0.1700
Data Index: 3788780 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.6672. Min Act: -0.1700
Data Index: 3850427 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.6047. Min Act: -0.1700
Data Index: 1954747 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1672. Min Range: -6.1672
Max Act: 5.5422. Min Act: -0.1700
Data Index: 5836363 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19