Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.3152. Min Act: -0.1700
Data Index: 8039824 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.1589. Min Act: -0.1700
Data Index: 5067619 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0964. Min Act: -0.1700
Data Index: 8470451 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0651. Min Act: -0.1700
Data Index: 2352377 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0339. Min Act: -0.1700
Data Index: 3547873 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0339. Min Act: -0.1700
Data Index: 3387167 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0339. Min Act: -0.1700
Data Index: 8485856 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9714. Min Act: -0.1700
Data Index: 2256384 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0026. Min Act: -0.1700
Data Index: 1172428 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0026. Min Act: -0.1700
Data Index: 7013201 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3152. Min Range: -4.3152
Max Act: 4.0026. Min Act: -0.1700
Data Index: 3515428 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9714. Min Act: -0.1700
Data Index: 2065877 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9714. Min Act: -0.1700
Data Index: 4563178 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9401. Min Act: -0.1700
Data Index: 3127781 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9714. Min Act: -0.1700
Data Index: 4445081 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9401. Min Act: -0.1700
Data Index: 724360 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9714. Min Act: -0.1700
Data Index: 2988352 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9401. Min Act: -0.1700
Data Index: 1834768 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9088. Min Act: -0.1700
Data Index: 229516 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3152. Min Range: -4.3152
Max Act: 3.9401. Min Act: -0.1700
Data Index: 4972383 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19