Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5673 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.8951. Min Act: -0.1700
Data Index: 2092351 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.6451. Min Act: -0.1700
Data Index: 3110673 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.5514. Min Act: -0.1700
Data Index: 8648313 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.2389. Min Act: -0.1700
Data Index: 8376849 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.2076. Min Act: -0.1700
Data Index: 1886128 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.1764. Min Act: -0.1700
Data Index: 2173782 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.1451. Min Act: -0.1700
Data Index: 6990778 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.1139. Min Act: -0.1700
Data Index: 4410138 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 6553316 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 4298989 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.1139. Min Act: -0.1700
Data Index: 8245143 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0201. Min Act: -0.1700
Data Index: 147624 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 2929856 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0514. Min Act: -0.1700
Data Index: 885917 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0514. Min Act: -0.1700
Data Index: 4916350 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0201. Min Act: -0.1700
Data Index: 2100039 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0201. Min Act: -0.1700
Data Index: 1298243 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8951. Min Range: -5.8951
Max Act: 4.9889. Min Act: -0.1700
Data Index: 4450514 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8951. Min Range: -5.8951
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3647809 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8951. Min Range: -5.8951
Max Act: 4.9889. Min Act: -0.1700
Data Index: 2316059 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19