Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.7843. Min Act: -0.1700
Data Index: 7791039 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.7531. Min Act: -0.1700
Data Index: 761334 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.6906. Min Act: -0.1700
Data Index: 7337381 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.6281. Min Act: -0.1700
Data Index: 4911138 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.5031. Min Act: -0.1700
Data Index: 5303490 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.5031. Min Act: -0.1700
Data Index: 6654338 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.4093. Min Act: -0.1700
Data Index: 2291497 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3781. Min Act: -0.1700
Data Index: 6850099 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.4093. Min Act: -0.1700
Data Index: 8820557 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3781. Min Act: -0.1700
Data Index: 7398121 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3781. Min Act: -0.1700
Data Index: 6193810 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3781. Min Act: -0.1700
Data Index: 7462834 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3468. Min Act: -0.1700
Data Index: 307038 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3156. Min Act: -0.1700
Data Index: 2907664 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.3156. Min Act: -0.1700
Data Index: 1302968 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.2843. Min Act: -0.1700
Data Index: 2028549 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.2843. Min Act: -0.1700
Data Index: 7821589 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.2843. Min Act: -0.1700
Data Index: 4507409 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.2843. Min Act: -0.1700
Data Index: 4124061 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7843. Min Range: -6.7843
Max Act: 6.2843. Min Act: -0.1700
Data Index: 8072176 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19