Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.6582. Min Act: -0.1700
Data Index: 1552752 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.1895. Min Act: -0.1700
Data Index: 8758147 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.1582. Min Act: -0.1700
Data Index: 6215890 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.1270. Min Act: -0.1700
Data Index: 5286275 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0957. Min Act: -0.1700
Data Index: 6502776 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0957. Min Act: -0.1700
Data Index: 7694437 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0957. Min Act: -0.1700
Data Index: 1153752 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0332. Min Act: -0.1700
Data Index: 8056286 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0332. Min Act: -0.1700
Data Index: 4535250 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0332. Min Act: -0.1700
Data Index: 5545082 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0332. Min Act: -0.1700
Data Index: 5905801 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0332. Min Act: -0.1700
Data Index: 3311666 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0020. Min Act: -0.1700
Data Index: 8358504 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0332. Min Act: -0.1700
Data Index: 6838405 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6582. Min Range: -5.6582
Max Act: 5.0020. Min Act: -0.1700
Data Index: 6057454 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6582. Min Range: -5.6582
Max Act: 4.9707. Min Act: -0.1700
Data Index: 1332836 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6582. Min Range: -5.6582
Max Act: 4.9707. Min Act: -0.1700
Data Index: 4219148 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6582. Min Range: -5.6582
Max Act: 4.9707. Min Act: -0.1700
Data Index: 4271163 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6582. Min Range: -5.6582
Max Act: 4.9395. Min Act: -0.1700
Data Index: 6863729 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6582. Min Range: -5.6582
Max Act: 4.9395. Min Act: -0.1700
Data Index: 8198625 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19