Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2347. Min Range: -6.2347
Max Act: 6.2347. Min Act: -0.1700
Data Index: 570368 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2347. Min Range: -6.2347
Max Act: 6.1722. Min Act: -0.1700
Data Index: 2899392 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2347. Min Range: -6.2347
Max Act: 6.0159. Min Act: -0.1700
Data Index: 2646437 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.9847. Min Act: -0.1700
Data Index: 2656004 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8909. Min Act: -0.1700
Data Index: 6083271 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8909. Min Act: -0.1700
Data Index: 8033887 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8597. Min Act: -0.1700
Data Index: 5264588 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4850619 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8284. Min Act: -0.1700
Data Index: 1139541 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8284. Min Act: -0.1700
Data Index: 3334133 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8597. Min Act: -0.1700
Data Index: 5000493 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.8284. Min Act: -0.1700
Data Index: 7237619 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7972. Min Act: -0.1700
Data Index: 1385034 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7347. Min Act: -0.1700
Data Index: 8764878 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7659. Min Act: -0.1700
Data Index: 611409 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6510684 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7347. Min Act: -0.1700
Data Index: 5991757 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7347. Min Act: -0.1700
Data Index: 299704 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.6722. Min Act: -0.1700
Data Index: 4352704 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2347. Min Range: -6.2347
Max Act: 5.7034. Min Act: -0.1700
Data Index: 6015815 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19