Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0790. Min Range: -6.0790
Max Act: 6.0790. Min Act: -0.1700
Data Index: 7750668 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0790. Min Range: -6.0790
Max Act: 6.0477. Min Act: -0.1700
Data Index: 7794003 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0790. Min Range: -6.0790
Max Act: 6.0477. Min Act: -0.1700
Data Index: 4955125 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.8290. Min Act: -0.1700
Data Index: 1436194 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.7665. Min Act: -0.1700
Data Index: 4955124 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.7352. Min Act: -0.1700
Data Index: 5263537 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6727. Min Act: -0.1700
Data Index: 8175025 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6415. Min Act: -0.1700
Data Index: 1248879 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6727. Min Act: -0.1700
Data Index: 8100903 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6415. Min Act: -0.1700
Data Index: 3754380 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6415. Min Act: -0.1700
Data Index: 3754379 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6102. Min Act: -0.1700
Data Index: 8449045 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.6102. Min Act: -0.1700
Data Index: 6557229 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5477. Min Act: -0.1700
Data Index: 6017489 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5477. Min Act: -0.1700
Data Index: 415331 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5477. Min Act: -0.1700
Data Index: 6989303 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5477. Min Act: -0.1700
Data Index: 6586751 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5165. Min Act: -0.1700
Data Index: 8407761 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5165. Min Act: -0.1700
Data Index: 1549565 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0790. Min Range: -6.0790
Max Act: 5.5165. Min Act: -0.1700
Data Index: 2458143 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19