Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.4889. Min Act: -0.1700
Data Index: 7457365 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.4264. Min Act: -0.1700
Data Index: 2678471 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.4576. Min Act: -0.1700
Data Index: 786378 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.3951. Min Act: -0.1700
Data Index: 1381043 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.3639. Min Act: -0.1700
Data Index: 4707643 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.3326. Min Act: -0.1700
Data Index: 6124115 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.3639. Min Act: -0.1700
Data Index: 6105901 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.3326. Min Act: -0.1700
Data Index: 5041036 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.3014. Min Act: -0.1700
Data Index: 8200772 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2389. Min Act: -0.1700
Data Index: 6626146 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2701. Min Act: -0.1700
Data Index: 8243127 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2389. Min Act: -0.1700
Data Index: 7742457 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2701. Min Act: -0.1700
Data Index: 2704892 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2389. Min Act: -0.1700
Data Index: 5212821 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2076. Min Act: -0.1700
Data Index: 3310910 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2389. Min Act: -0.1700
Data Index: 6350383 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2389. Min Act: -0.1700
Data Index: 739123 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2076. Min Act: -0.1700
Data Index: 1467969 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2389. Min Act: -0.1700
Data Index: 6848239 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4889. Min Range: -5.4889
Max Act: 5.2076. Min Act: -0.1700
Data Index: 1594523 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19