Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1749. Min Range: -9.1749
Max Act: 9.1749. Min Act: -0.1700
Data Index: 4319890 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1749. Min Range: -9.1749
Max Act: 9.1124. Min Act: -0.1700
Data Index: 2246962 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.8624. Min Act: -0.1700
Data Index: 1536048 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.7374. Min Act: -0.1700
Data Index: 7739643 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.6749. Min Act: -0.1700
Data Index: 2516251 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.4249. Min Act: -0.1700
Data Index: 2231777 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.2999. Min Act: -0.1700
Data Index: 183677 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.2999. Min Act: -0.1700
Data Index: 3644274 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.2999. Min Act: -0.1700
Data Index: 4684385 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.1749. Min Act: -0.1700
Data Index: 8512839 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.2374. Min Act: -0.1700
Data Index: 8601592 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.2374. Min Act: -0.1700
Data Index: 552157 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.1124. Min Act: -0.1700
Data Index: 381047 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.0499. Min Act: -0.1700
Data Index: 5329947 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.0499. Min Act: -0.1700
Data Index: 8012528 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.0499. Min Act: -0.1700
Data Index: 7422135 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.0499. Min Act: -0.1700
Data Index: 8535785 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1749. Min Range: -9.1749
Max Act: 8.0499. Min Act: -0.1700
Data Index: 7074185 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1749. Min Range: -9.1749
Max Act: 7.9874. Min Act: -0.1700
Data Index: 5911280 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1749. Min Range: -9.1749
Max Act: 7.9874. Min Act: -0.1700
Data Index: 1482350 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19