Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.7693. Min Act: -0.1700
Data Index: 475042 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.8318. Min Act: -0.1693
Data Index: 3861173 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.5818. Min Act: -0.1700
Data Index: 221313 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.6443. Min Act: -0.1700
Data Index: 8376165 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.5818. Min Act: -0.1694
Data Index: 1669388 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.5193. Min Act: -0.1695
Data Index: 7860995 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.4881. Min Act: -0.1700
Data Index: 8605860 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.4881. Min Act: -0.1700
Data Index: 7171111 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.4881. Min Act: -0.1700
Data Index: 1403419 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.4881. Min Act: -0.1700
Data Index: 2107473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.4256. Min Act: -0.1700
Data Index: 616851 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1699
Data Index: 4842968 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1699
Data Index: 349724 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1700
Data Index: 784931 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3318. Min Act: -0.1700
Data Index: 1568273 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1700
Data Index: 1349286 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1700
Data Index: 6769810 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3318. Min Act: -0.1699
Data Index: 8380775 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1693
Data Index: 8474779 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8318. Min Range: -6.8318
Max Act: 6.3943. Min Act: -0.1697
Data Index: 3832764 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19