Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3585. Min Range: -8.3585
Max Act: 8.3585. Min Act: -0.1700
Data Index: 18012 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.8897. Min Act: -0.1700
Data Index: 5544536 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.8585. Min Act: -0.1700
Data Index: 133179 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.8585. Min Act: -0.1700
Data Index: 1813087 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.7647. Min Act: -0.1700
Data Index: 4319365 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.7960. Min Act: -0.1700
Data Index: 1809448 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.7022. Min Act: -0.1700
Data Index: 1296192 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.6710. Min Act: -0.1700
Data Index: 1594316 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.6085. Min Act: -0.1700
Data Index: 6851958 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.5460. Min Act: -0.1700
Data Index: 1121440 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.4835. Min Act: -0.1700
Data Index: 656398 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.4522. Min Act: -0.1700
Data Index: 5257299 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.4210. Min Act: -0.1700
Data Index: 4280799 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.4210. Min Act: -0.1700
Data Index: 570746 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.3897. Min Act: -0.1700
Data Index: 3879758 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.3897. Min Act: -0.1700
Data Index: 4157243 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.3897. Min Act: -0.1700
Data Index: 1331219 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.3897. Min Act: -0.1700
Data Index: 8175311 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.3585. Min Act: -0.1700
Data Index: 3500951 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3585. Min Range: -8.3585
Max Act: 7.3272. Min Act: -0.1700
Data Index: 58668 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19