Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.8787. Min Act: -0.1700
Data Index: 7029759 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.8474. Min Act: -0.1700
Data Index: 6882726 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.8162. Min Act: -0.1700
Data Index: 4800964 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.7537. Min Act: -0.1700
Data Index: 6247610 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.7537. Min Act: -0.1700
Data Index: 6199540 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.7224. Min Act: -0.1700
Data Index: 2871044 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.7224. Min Act: -0.1700
Data Index: 2846315 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.7224. Min Act: -0.1700
Data Index: 6247606 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6912. Min Act: -0.1700
Data Index: 808369 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6912. Min Act: -0.1700
Data Index: 8817859 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6599. Min Act: -0.1700
Data Index: 2727275 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6599. Min Act: -0.1700
Data Index: 6247602 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6912. Min Act: -0.1700
Data Index: 2595894 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6599. Min Act: -0.1700
Data Index: 4395236 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.6287. Min Act: -0.1700
Data Index: 8426784 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.5974. Min Act: -0.1700
Data Index: 2928024 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.5974. Min Act: -0.1700
Data Index: 8258644 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.5974. Min Act: -0.1700
Data Index: 4250599 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.5662. Min Act: -0.1700
Data Index: 3447634 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8787. Min Range: -5.8787
Max Act: 5.5974. Min Act: -0.1700
Data Index: 7081442 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19