Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 116 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.5788. Min Act: -0.1700
Data Index: 1431185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.3288. Min Act: -0.1700
Data Index: 1683070 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.2663. Min Act: -0.1700
Data Index: 6235602 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.2038. Min Act: -0.1700
Data Index: 6954950 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5159282 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.1413. Min Act: -0.1700
Data Index: 5159284 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.1413. Min Act: -0.1700
Data Index: 8009890 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.1100. Min Act: -0.1700
Data Index: 39254 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.0788. Min Act: -0.1700
Data Index: 1431184 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.1100. Min Act: -0.1700
Data Index: 3376844 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.0788. Min Act: -0.1700
Data Index: 6347629 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.0788. Min Act: -0.1700
Data Index: 626201 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.0475. Min Act: -0.1700
Data Index: 7996820 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.0475. Min Act: -0.1700
Data Index: 2347900 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5788. Min Range: -5.5788
Max Act: 5.0475. Min Act: -0.1700
Data Index: 3863737 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5788. Min Range: -5.5788
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5923764 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5788. Min Range: -5.5788
Max Act: 4.9850. Min Act: -0.1700
Data Index: 4043618 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5788. Min Range: -5.5788
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3558978 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5788. Min Range: -5.5788
Max Act: 4.9225. Min Act: -0.1700
Data Index: 5788873 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5788. Min Range: -5.5788
Max Act: 4.9225. Min Act: -0.1700
Data Index: 1683071 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19