Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.6172. Min Act: -0.1700
Data Index: 2321623 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.4297. Min Act: -0.1700
Data Index: 6008155 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.3047. Min Act: -0.1700
Data Index: 3520602 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.2734. Min Act: -0.1700
Data Index: 3465686 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.2109. Min Act: -0.1700
Data Index: 7745622 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.2109. Min Act: -0.1700
Data Index: 7405864 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.1797. Min Act: -0.1700
Data Index: 564324 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.1484. Min Act: -0.1700
Data Index: 2342974 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.1484. Min Act: -0.1700
Data Index: 6179775 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.1484. Min Act: -0.1700
Data Index: 2856281 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0547. Min Act: -0.1700
Data Index: 6179776 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0859. Min Act: -0.1700
Data Index: 5182741 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0859. Min Act: -0.1700
Data Index: 288031 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0547. Min Act: -0.1700
Data Index: 4023919 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0859. Min Act: -0.1700
Data Index: 3927970 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0234. Min Act: -0.1700
Data Index: 2285630 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0547. Min Act: -0.1700
Data Index: 2220941 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0547. Min Act: -0.1700
Data Index: 1400637 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0547. Min Act: -0.1700
Data Index: 6979592 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6172. Min Range: -5.6172
Max Act: 5.0234. Min Act: -0.1700
Data Index: 3419672 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19