Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.4532. Min Act: -0.1700
Data Index: 979812 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.3907. Min Act: -0.1700
Data Index: 1778154 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.3595. Min Act: -0.1700
Data Index: 3762693 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.3282. Min Act: -0.1700
Data Index: 1455376 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.3282. Min Act: -0.1700
Data Index: 7883346 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2970. Min Act: -0.1700
Data Index: 4314243 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2657. Min Act: -0.1700
Data Index: 5079822 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2345. Min Act: -0.1700
Data Index: 8213329 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2345. Min Act: -0.1700
Data Index: 6431721 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2345. Min Act: -0.1700
Data Index: 3511890 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2032. Min Act: -0.1700
Data Index: 7218065 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.2032. Min Act: -0.1700
Data Index: 1076191 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1720. Min Act: -0.1699
Data Index: 1782786 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1720. Min Act: -0.1700
Data Index: 4701831 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1720. Min Act: -0.1700
Data Index: 1760417 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1720. Min Act: -0.1697
Data Index: 6867695 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1407. Min Act: -0.1700
Data Index: 3505257 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1407. Min Act: -0.1700
Data Index: 2217203 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1407. Min Act: -0.1700
Data Index: 3366893 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4532. Min Range: -4.4532
Max Act: 4.1407. Min Act: -0.1700
Data Index: 2674438 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19