Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2188 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.2279. Min Act: -0.1700
Data Index: 6118256 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.2279. Min Act: -0.1700
Data Index: 564032 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1654. Min Act: -0.1700
Data Index: 5354019 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1967. Min Act: -0.1700
Data Index: 212727 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1967. Min Act: -0.1700
Data Index: 2767419 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1654. Min Act: -0.1700
Data Index: 6753471 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1654. Min Act: -0.1700
Data Index: 6006193 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1342. Min Act: -0.1700
Data Index: 2312279 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1342. Min Act: -0.1700
Data Index: 6809801 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1342. Min Act: -0.1700
Data Index: 6590297 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.0717. Min Act: -0.1700
Data Index: 2742011 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1029. Min Act: -0.1700
Data Index: 2334731 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1029. Min Act: -0.1700
Data Index: 4210024 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1029. Min Act: -0.1700
Data Index: 1227933 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1029. Min Act: -0.1700
Data Index: 6469681 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3445135 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1029. Min Act: -0.1700
Data Index: 5961111 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.0404. Min Act: -0.1700
Data Index: 5953486 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.1029. Min Act: -0.1700
Data Index: 2224699 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2279. Min Range: -5.2279
Max Act: 5.0717. Min Act: -0.1700
Data Index: 5028441 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19