Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4951. Min Act: -0.1700
Data Index: 2541290 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.4013. Min Act: -0.1700
Data Index: 2316447 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.3701. Min Act: -0.1700
Data Index: 149753 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.3076. Min Act: -0.1700
Data Index: 578983 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.2138. Min Act: -0.1700
Data Index: 459091 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1826. Min Act: -0.1700
Data Index: 1069753 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1826. Min Act: -0.1700
Data Index: 2096046 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1826. Min Act: -0.1700
Data Index: 7947462 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1826. Min Act: -0.1700
Data Index: 5861044 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1513. Min Act: -0.1700
Data Index: 3533144 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 4810109 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 2490254 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 4185824 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 5795080 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 2796118 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 6079869 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.1201. Min Act: -0.1700
Data Index: 1069754 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.0888. Min Act: -0.1700
Data Index: 3084249 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.0576. Min Act: -0.1700
Data Index: 3547258 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4951. Min Range: -5.4951
Max Act: 5.0576. Min Act: -0.1700
Data Index: 4190446 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19