Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1046 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2536. Min Range: -6.2536
Max Act: 6.2536. Min Act: -0.1700
Data Index: 5121079 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2536. Min Range: -6.2536
Max Act: 6.1599. Min Act: -0.1700
Data Index: 7997907 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2536. Min Range: -6.2536
Max Act: 6.0974. Min Act: -0.1700
Data Index: 7951326 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.9724. Min Act: -0.1700
Data Index: 1378388 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.9411. Min Act: -0.1700
Data Index: 548027 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.9724. Min Act: -0.1700
Data Index: 4653386 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.9099. Min Act: -0.1700
Data Index: 5658585 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.9099. Min Act: -0.1700
Data Index: 8307056 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.8474. Min Act: -0.1700
Data Index: 3278941 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.9099. Min Act: -0.1700
Data Index: 1961403 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.8474. Min Act: -0.1700
Data Index: 622126 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.8474. Min Act: -0.1700
Data Index: 3792174 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.8161. Min Act: -0.1700
Data Index: 8788627 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.8161. Min Act: -0.1700
Data Index: 431378 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.8161. Min Act: -0.1700
Data Index: 6517797 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.7849. Min Act: -0.1700
Data Index: 2098001 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.7849. Min Act: -0.1700
Data Index: 310047 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.7849. Min Act: -0.1700
Data Index: 2477444 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.7849. Min Act: -0.1700
Data Index: 7627089 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2536. Min Range: -6.2536
Max Act: 5.7224. Min Act: -0.1700
Data Index: 558063 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19