Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4841 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0195. Min Range: -6.0195
Max Act: 6.0195. Min Act: -0.1700
Data Index: 6735590 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.8320. Min Act: -0.1700
Data Index: 2231276 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.8320. Min Act: -0.1700
Data Index: 1216875 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.8632. Min Act: -0.1700
Data Index: 3739154 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7695. Min Act: -0.1700
Data Index: 2871599 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7382. Min Act: -0.1700
Data Index: 2432030 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7382. Min Act: -0.1700
Data Index: 3895583 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7382. Min Act: -0.1700
Data Index: 998607 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7070. Min Act: -0.1700
Data Index: 4289434 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7070. Min Act: -0.1700
Data Index: 5852452 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 2985689 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.7070. Min Act: -0.1700
Data Index: 6399337 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 1945857 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 7788302 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 7383878 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 3731423 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 1218729 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6757. Min Act: -0.1700
Data Index: 1200533 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6445. Min Act: -0.1700
Data Index: 3600750 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0195. Min Range: -6.0195
Max Act: 5.6132. Min Act: -0.1700
Data Index: 6549568 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19