Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.4523. Min Act: -0.1700
Data Index: 6117249 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.2647. Min Act: -0.1700
Data Index: 2199232 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.2022. Min Act: -0.1700
Data Index: 2554084 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.1397. Min Act: -0.1700
Data Index: 7923367 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.1397. Min Act: -0.1700
Data Index: 1399161 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0460. Min Act: -0.1700
Data Index: 4061197 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0460. Min Act: -0.1700
Data Index: 6185117 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0460. Min Act: -0.1700
Data Index: 7521619 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0147. Min Act: -0.1700
Data Index: 8677028 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0147. Min Act: -0.1700
Data Index: 1022838 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0147. Min Act: -0.1700
Data Index: 2363673 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4523. Min Range: -4.4523
Max Act: 4.0147. Min Act: -0.1700
Data Index: 705208 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 5615889 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 5134912 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 3279509 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9522. Min Act: -0.1700
Data Index: 4142963 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 51601 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 866248 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 4924701 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4523. Min Range: -4.4523
Max Act: 3.9834. Min Act: -0.1700
Data Index: 1101345 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19