Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.9540. Min Act: -0.1700
Data Index: 3375248 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4044088 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.8915. Min Act: -0.1700
Data Index: 422409 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.8602. Min Act: -0.1700
Data Index: 7635037 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.8290. Min Act: -0.1700
Data Index: 8128640 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.8290. Min Act: -0.1700
Data Index: 2719354 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.7665. Min Act: -0.1700
Data Index: 5211213 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.7352. Min Act: -0.1700
Data Index: 4485012 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.7352. Min Act: -0.1700
Data Index: 5752047 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.7040. Min Act: -0.1700
Data Index: 3500961 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.7040. Min Act: -0.1700
Data Index: 5010215 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.6102. Min Act: -0.1700
Data Index: 8232345 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.6102. Min Act: -0.1700
Data Index: 5328798 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.6415. Min Act: -0.1700
Data Index: 5998637 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.6102. Min Act: -0.1700
Data Index: 6216791 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.6102. Min Act: -0.1700
Data Index: 6487233 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.6415. Min Act: -0.1700
Data Index: 4678139 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.5790. Min Act: -0.1700
Data Index: 115418 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.5790. Min Act: -0.1700
Data Index: 7326294 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9540. Min Range: -5.9540
Max Act: 5.5477. Min Act: -0.1700
Data Index: 2323760 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19