Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 3575608 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.3323. Min Act: -0.1700
Data Index: 1481493 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2698. Min Act: -0.1700
Data Index: 1719230 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1761. Min Act: -0.1700
Data Index: 1719237 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1448. Min Act: -0.1700
Data Index: 7555184 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1136. Min Act: -0.1700
Data Index: 5008012 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1136. Min Act: -0.1700
Data Index: 686334 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.9886. Min Act: -0.1700
Data Index: 4063231 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.9261. Min Act: -0.1700
Data Index: 3575604 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8948. Min Act: -0.1700
Data Index: 7151014 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8636. Min Act: -0.1700
Data Index: 1119208 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8636. Min Act: -0.1700
Data Index: 3561837 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8948. Min Act: -0.1700
Data Index: 4362617 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5236872 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8636. Min Act: -0.1700
Data Index: 2920532 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 1719248 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 3561838 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 7378866 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 218569 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 6459272 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19