Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1293. Min Range: -8.1293
Max Act: 8.1293. Min Act: -0.1700
Data Index: 6769601 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.8168. Min Act: -0.1700
Data Index: 5641215 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.6918. Min Act: -0.1700
Data Index: 7792831 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 3441830 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.6293. Min Act: -0.1700
Data Index: 6434742 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 7120423 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 2910834 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 5112113 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 2214468 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 630750 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5980. Min Act: -0.1700
Data Index: 6263851 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5668. Min Act: -0.1700
Data Index: 6124149 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5668. Min Act: -0.1700
Data Index: 2905217 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5043. Min Act: -0.1700
Data Index: 1640589 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.5043. Min Act: -0.1700
Data Index: 344698 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.4418. Min Act: -0.1700
Data Index: 6998578 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.4730. Min Act: -0.1700
Data Index: 7304807 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.4730. Min Act: -0.1700
Data Index: 2114455 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.4418. Min Act: -0.1700
Data Index: 677937 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1293. Min Range: -8.1293
Max Act: 7.4105. Min Act: -0.1700
Data Index: 7241582 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19