Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.4148. Min Act: -0.1700
Data Index: 2394126 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.4148. Min Act: -0.1700
Data Index: 703050 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.3835. Min Act: -0.1700
Data Index: 5221660 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.3523. Min Act: -0.1700
Data Index: 3857461 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.2898. Min Act: -0.1700
Data Index: 1544900 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.2898. Min Act: -0.1700
Data Index: 2466757 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.2585. Min Act: -0.1700
Data Index: 7005715 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.2585. Min Act: -0.1700
Data Index: 1064258 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.2273. Min Act: -0.1700
Data Index: 6733223 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.2273. Min Act: -0.1700
Data Index: 586546 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1960. Min Act: -0.1700
Data Index: 7553172 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1647. Min Act: -0.1700
Data Index: 3493611 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1647. Min Act: -0.1700
Data Index: 235309 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1647. Min Act: -0.1700
Data Index: 1327931 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1335. Min Act: -0.1700
Data Index: 2651714 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1335. Min Act: -0.1700
Data Index: 1910948 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1335. Min Act: -0.1700
Data Index: 2735497 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1647. Min Act: -0.1700
Data Index: 5053586 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1647. Min Act: -0.1700
Data Index: 4871383 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4148. Min Range: -4.4148
Max Act: 4.1335. Min Act: -0.1700
Data Index: 8295875 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19