Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.4534. Min Act: -0.1700
Data Index: 4104695 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.2346. Min Act: -0.1700
Data Index: 1931736 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.2033. Min Act: -0.1700
Data Index: 7296936 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 482973 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 6804906 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 3970503 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 6452852 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 8449960 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 7840810 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1408. Min Act: -0.1700
Data Index: 5624584 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 3386585 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1408. Min Act: -0.1700
Data Index: 3203933 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 1701763 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1408. Min Act: -0.1700
Data Index: 4186320 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1408. Min Act: -0.1700
Data Index: 1228207 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 521030 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 1234341 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 2319790 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1408. Min Act: -0.1700
Data Index: 5136222 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 2945267 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19