Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6988. Min Range: -9.6988
Max Act: 9.6988. Min Act: -0.1700
Data Index: 8090302 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6988. Min Range: -9.6988
Max Act: 9.2613. Min Act: -0.1700
Data Index: 7475194 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.9488. Min Act: -0.1700
Data Index: 6217677 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.9488. Min Act: -0.1700
Data Index: 5921486 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.9488. Min Act: -0.1700
Data Index: 7439352 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.8238. Min Act: -0.1700
Data Index: 7857786 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.6988. Min Act: -0.1700
Data Index: 2201772 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.5738. Min Act: -0.1700
Data Index: 7099199 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.6363. Min Act: -0.1700
Data Index: 5672163 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.6363. Min Act: -0.1700
Data Index: 3539874 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.5738. Min Act: -0.1700
Data Index: 8694453 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.5113. Min Act: -0.1700
Data Index: 3839402 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.5738. Min Act: -0.1700
Data Index: 3722271 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.4488. Min Act: -0.1700
Data Index: 5492102 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.3863. Min Act: -0.1700
Data Index: 5902908 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.3863. Min Act: -0.1700
Data Index: 8780281 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.3238. Min Act: -0.1700
Data Index: 2647473 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.2613. Min Act: -0.1700
Data Index: 263946 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.2613. Min Act: -0.1700
Data Index: 3250336 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6988. Min Range: -9.6988
Max Act: 8.2613. Min Act: -0.1700
Data Index: 460987 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19