Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1532. Min Range: -8.1532
Max Act: 8.1532. Min Act: -0.1700
Data Index: 4846982 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1532. Min Range: -8.1532
Max Act: 8.0907. Min Act: -0.1700
Data Index: 3188062 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1532. Min Range: -8.1532
Max Act: 8.0282. Min Act: -0.1700
Data Index: 1034849 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.9657. Min Act: -0.1700
Data Index: 2899157 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.9657. Min Act: -0.1700
Data Index: 3002104 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.9032. Min Act: -0.1700
Data Index: 2591422 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.9032. Min Act: -0.1700
Data Index: 1378693 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.9657. Min Act: -0.1700
Data Index: 2238620 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.8407. Min Act: -0.1700
Data Index: 3850167 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.8407. Min Act: -0.1700
Data Index: 7742782 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.8407. Min Act: -0.1700
Data Index: 5025226 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.9032. Min Act: -0.1700
Data Index: 3794690 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7469. Min Act: -0.1700
Data Index: 1768990 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7782. Min Act: -0.1700
Data Index: 6012860 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7469. Min Act: -0.1700
Data Index: 259782 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7469. Min Act: -0.1700
Data Index: 6527657 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7157. Min Act: -0.1700
Data Index: 7437894 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7469. Min Act: -0.1700
Data Index: 6730362 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7157. Min Act: -0.1700
Data Index: 4357540 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1532. Min Range: -8.1532
Max Act: 7.7157. Min Act: -0.1700
Data Index: 2988118 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19