Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2131 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.4855. Min Act: -0.1700
Data Index: 4258284 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.4542. Min Act: -0.1700
Data Index: 777611 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.4230. Min Act: -0.1700
Data Index: 855979 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.3917. Min Act: -0.1700
Data Index: 1172463 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.3605. Min Act: -0.1700
Data Index: 8592009 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.3605. Min Act: -0.1700
Data Index: 5425439 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.3605. Min Act: -0.1700
Data Index: 499751 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.3292. Min Act: -0.1700
Data Index: 3307837 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2980. Min Act: -0.1700
Data Index: 5893154 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2980. Min Act: -0.1700
Data Index: 8449588 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2667. Min Act: -0.1700
Data Index: 3992002 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2355. Min Act: -0.1700
Data Index: 941160 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2355. Min Act: -0.1700
Data Index: 7665505 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2042. Min Act: -0.1700
Data Index: 8597216 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2042. Min Act: -0.1700
Data Index: 7369131 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2042. Min Act: -0.1700
Data Index: 3380994 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.2042. Min Act: -0.1700
Data Index: 944079 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.1417. Min Act: -0.1700
Data Index: 6317702 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.1417. Min Act: -0.1700
Data Index: 2878793 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4855. Min Range: -6.4855
Max Act: 6.1417. Min Act: -0.1700
Data Index: 1089524 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19