Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.6153. Min Act: -0.1700
Data Index: 3059442 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.5215. Min Act: -0.1700
Data Index: 8784542 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.4278. Min Act: -0.1700
Data Index: 3368497 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.3028. Min Act: -0.1700
Data Index: 7806849 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.3028. Min Act: -0.1700
Data Index: 8048586 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.2715. Min Act: -0.1700
Data Index: 2507216 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.2403. Min Act: -0.1700
Data Index: 8039109 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.2403. Min Act: -0.1700
Data Index: 8690869 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.2403. Min Act: -0.1700
Data Index: 3616356 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.2090. Min Act: -0.1700
Data Index: 3407437 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.2090. Min Act: -0.1700
Data Index: 5457326 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1778. Min Act: -0.1700
Data Index: 8182809 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1778. Min Act: -0.1700
Data Index: 6757555 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1778. Min Act: -0.1700
Data Index: 8554457 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1153. Min Act: -0.1700
Data Index: 6340056 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1465. Min Act: -0.1700
Data Index: 5257267 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1465. Min Act: -0.1700
Data Index: 107554 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1465. Min Act: -0.1700
Data Index: 8800434 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.1465. Min Act: -0.1700
Data Index: 1772565 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6153. Min Range: -5.6153
Max Act: 5.0840. Min Act: -0.1700
Data Index: 4111116 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19