Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 235 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4322. Min Range: -3.4322
Max Act: 3.4322. Min Act: -0.1697
Data Index: 8759535 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4322. Min Range: -3.4322
Max Act: 3.2282. Min Act: -0.1700
Data Index: 7483004 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4322. Min Range: -3.4322
Max Act: 3.1968. Min Act: -0.1700
Data Index: 3884385 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4322. Min Range: -3.4322
Max Act: 3.1181. Min Act: -0.1691
Data Index: 6314196 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4322. Min Range: -3.4322
Max Act: 3.0392. Min Act: -0.1699
Data Index: 1729591 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4322. Min Range: -3.4322
Max Act: 3.0077. Min Act: -0.1635
Data Index: 1081146 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.9760. Min Act: -0.1700
Data Index: 7573071 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.9602. Min Act: -0.1700
Data Index: 3105242 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.9602. Min Act: -0.1700
Data Index: 6748927 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8810. Min Act: -0.1670
Data Index: 546936 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.9285. Min Act: -0.1700
Data Index: 6030312 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.9127. Min Act: -0.1700
Data Index: 4456622 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8968. Min Act: -0.1484
Data Index: 8759539 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8810. Min Act: -0.1700
Data Index: 8158520 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.9127. Min Act: -0.1700
Data Index: 4472258 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8651. Min Act: -0.1700
Data Index: 2152394 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8651. Min Act: -0.1700
Data Index: 1604571 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8651. Min Act: -0.1517
Data Index: 1999748 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8492. Min Act: -0.1700
Data Index: 8246883 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4322. Min Range: -3.4322
Max Act: 2.8492. Min Act: -0.1700
Data Index: 8267489 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19