Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5364. Min Range: -6.5364
Max Act: 6.5364. Min Act: -0.1700
Data Index: 6987137 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5364. Min Range: -6.5364
Max Act: 6.3489. Min Act: -0.1700
Data Index: 2195515 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5364. Min Range: -6.5364
Max Act: 6.1614. Min Act: -0.1700
Data Index: 1328846 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5364. Min Range: -6.5364
Max Act: 6.0364. Min Act: -0.1700
Data Index: 772500 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.9739. Min Act: -0.1700
Data Index: 2527867 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.9427. Min Act: -0.1700
Data Index: 3551609 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.9114. Min Act: -0.1700
Data Index: 3617260 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 130461 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 46363 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.8489. Min Act: -0.1700
Data Index: 2502999 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6290581 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.7864. Min Act: -0.1700
Data Index: 453696 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.7864. Min Act: -0.1700
Data Index: 1441773 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.7552. Min Act: -0.1700
Data Index: 7835641 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.7239. Min Act: -0.1700
Data Index: 2894616 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.7239. Min Act: -0.1700
Data Index: 2997201 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.6927. Min Act: -0.1700
Data Index: 2796454 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.6927. Min Act: -0.1700
Data Index: 3409840 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.7239. Min Act: -0.1700
Data Index: 4169573 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5364. Min Range: -6.5364
Max Act: 5.6927. Min Act: -0.1700
Data Index: 7349247 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19