Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5025 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.4489. Min Act: -0.1700
Data Index: 4137390 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.3864. Min Act: -0.1700
Data Index: 4729629 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.3551. Min Act: -0.1700
Data Index: 5501745 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2926. Min Act: -0.1700
Data Index: 6266260 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2614. Min Act: -0.1700
Data Index: 6815365 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2301. Min Act: -0.1700
Data Index: 4796975 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2614. Min Act: -0.1700
Data Index: 7170692 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2926. Min Act: -0.1700
Data Index: 819764 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2301. Min Act: -0.1700
Data Index: 1833625 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2614. Min Act: -0.1700
Data Index: 1021933 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.2301. Min Act: -0.1700
Data Index: 5981168 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1989. Min Act: -0.1700
Data Index: 51241 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1989. Min Act: -0.1700
Data Index: 5260355 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1989. Min Act: -0.1700
Data Index: 5999248 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1676. Min Act: -0.1700
Data Index: 6330919 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1676. Min Act: -0.1700
Data Index: 2096222 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1364. Min Act: -0.1700
Data Index: 3138638 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1364. Min Act: -0.1700
Data Index: 6229875 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.1051. Min Act: -0.1700
Data Index: 3506713 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4489. Min Range: -4.4489
Max Act: 4.0739. Min Act: -0.1700
Data Index: 3039407 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19