Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.4236. Min Act: -0.1700
Data Index: 3508254 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.3299. Min Act: -0.1700
Data Index: 3689823 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.2674. Min Act: -0.1700
Data Index: 609424 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.2361. Min Act: -0.1700
Data Index: 5395125 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 3468446 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 903540 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.2049. Min Act: -0.1700
Data Index: 4480008 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 2315083 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1424. Min Act: -0.1700
Data Index: 6623557 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 862394 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 2525209 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0799. Min Act: -0.1700
Data Index: 6398161 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0799. Min Act: -0.1700
Data Index: 7262586 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0799. Min Act: -0.1700
Data Index: 7771855 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0799. Min Act: -0.1700
Data Index: 475832 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.1111. Min Act: -0.1700
Data Index: 4412358 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0486. Min Act: -0.1700
Data Index: 7375641 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0486. Min Act: -0.1700
Data Index: 7484711 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0174. Min Act: -0.1700
Data Index: 4711558 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4236. Min Range: -6.4236
Max Act: 6.0174. Min Act: -0.1700
Data Index: 598167 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19