Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3674. Min Range: -8.3674
Max Act: 8.3674. Min Act: -0.1700
Data Index: 8600408 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3674. Min Range: -8.3674
Max Act: 8.0237. Min Act: -0.1700
Data Index: 2669710 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.8362. Min Act: -0.1700
Data Index: 4225330 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.8674. Min Act: -0.1700
Data Index: 4616321 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.8674. Min Act: -0.1700
Data Index: 37707 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.8049. Min Act: -0.1700
Data Index: 4225331 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7424. Min Act: -0.1700
Data Index: 4262795 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7737. Min Act: -0.1700
Data Index: 2190127 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7424. Min Act: -0.1700
Data Index: 4687631 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7424. Min Act: -0.1700
Data Index: 160274 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 4096240 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7424. Min Act: -0.1700
Data Index: 8600406 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 6604241 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7737. Min Act: -0.1700
Data Index: 8600405 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 6111498 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 5732972 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 8371498 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 8501262 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 3256604 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3674. Min Range: -8.3674
Max Act: 7.7112. Min Act: -0.1700
Data Index: 6181925 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19