Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5830 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4913. Min Range: -5.4913
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5213382 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4913. Min Range: -5.4913
Max Act: 5.2413. Min Act: -0.1700
Data Index: 5213381 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4913. Min Range: -5.4913
Max Act: 5.0538. Min Act: -0.1700
Data Index: 1368350 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4913. Min Range: -5.4913
Max Act: 5.0538. Min Act: -0.1700
Data Index: 1670690 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.9913. Min Act: -0.1700
Data Index: 7514013 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.9601. Min Act: -0.1700
Data Index: 8470346 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.9288. Min Act: -0.1700
Data Index: 552771 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8976. Min Act: -0.1700
Data Index: 4951317 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8976. Min Act: -0.1700
Data Index: 1670701 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 7594300 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 4773881 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8351. Min Act: -0.1700
Data Index: 5683663 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 4393144 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8663. Min Act: -0.1700
Data Index: 2650289 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5683664 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8351. Min Act: -0.1700
Data Index: 5081197 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 1038706 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.8038. Min Act: -0.1700
Data Index: 1957902 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.7726. Min Act: -0.1700
Data Index: 2745944 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4913. Min Range: -5.4913
Max Act: 4.7726. Min Act: -0.1700
Data Index: 3991531 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19