Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.6896. Min Act: -0.1700
Data Index: 3097941 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.6584. Min Act: -0.1700
Data Index: 2980155 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.6271. Min Act: -0.1700
Data Index: 3824300 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.5334. Min Act: -0.1700
Data Index: 2965093 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.4709. Min Act: -0.1700
Data Index: 5816352 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.3459. Min Act: -0.1700
Data Index: 4801365 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.3146. Min Act: -0.1700
Data Index: 4494043 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.2834. Min Act: -0.1700
Data Index: 8102769 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.2209. Min Act: -0.1700
Data Index: 5045361 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.2209. Min Act: -0.1700
Data Index: 105911 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1896. Min Act: -0.1700
Data Index: 6676820 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1896. Min Act: -0.1700
Data Index: 6815033 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1584. Min Act: -0.1700
Data Index: 6568844 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1584. Min Act: -0.1700
Data Index: 1136526 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1271. Min Act: -0.1700
Data Index: 7563879 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1271. Min Act: -0.1700
Data Index: 8730673 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0334. Min Act: -0.1700
Data Index: 358043 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0959. Min Act: -0.1700
Data Index: 2529508 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0334. Min Act: -0.1700
Data Index: 6994795 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0646. Min Act: -0.1700
Data Index: 4507402 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19