Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.8605. Min Act: -0.1700
Data Index: 6153200 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.7667. Min Act: -0.1700
Data Index: 3507944 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.7355. Min Act: -0.1700
Data Index: 4182991 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.7042. Min Act: -0.1700
Data Index: 6736454 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.6730. Min Act: -0.1700
Data Index: 7132722 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.7042. Min Act: -0.1700
Data Index: 5530035 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.6730. Min Act: -0.1700
Data Index: 7657310 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.6417. Min Act: -0.1700
Data Index: 6872542 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.6417. Min Act: -0.1700
Data Index: 7519770 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.6417. Min Act: -0.1700
Data Index: 8520681 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.6105. Min Act: -0.1700
Data Index: 5521228 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.5480. Min Act: -0.1700
Data Index: 7523884 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.5167. Min Act: -0.1700
Data Index: 8089595 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.5167. Min Act: -0.1700
Data Index: 8377572 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.5167. Min Act: -0.1700
Data Index: 6912631 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.4855. Min Act: -0.1700
Data Index: 2527551 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.4855. Min Act: -0.1700
Data Index: 8767524 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.4855. Min Act: -0.1700
Data Index: 8189208 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.4542. Min Act: -0.1700
Data Index: 62113 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8605. Min Range: -6.8605
Max Act: 6.4230. Min Act: -0.1700
Data Index: 6271118 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19