Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4516. Min Range: -6.4516
Max Act: 6.4516. Min Act: -0.1700
Data Index: 410474 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4516. Min Range: -6.4516
Max Act: 6.0453. Min Act: -0.1700
Data Index: 2467399 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4516. Min Range: -6.4516
Max Act: 6.0141. Min Act: -0.1700
Data Index: 7300740 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4516. Min Range: -6.4516
Max Act: 6.0141. Min Act: -0.1700
Data Index: 5666522 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.9203. Min Act: -0.1700
Data Index: 6178253 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.9203. Min Act: -0.1700
Data Index: 851384 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.8891. Min Act: -0.1700
Data Index: 7888052 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.8578. Min Act: -0.1700
Data Index: 5075604 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.8578. Min Act: -0.1700
Data Index: 3425439 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.8578. Min Act: -0.1700
Data Index: 1650776 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.8266. Min Act: -0.1700
Data Index: 2156411 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 6435310 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7953. Min Act: -0.1700
Data Index: 2319746 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7641. Min Act: -0.1700
Data Index: 7799940 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7328. Min Act: -0.1700
Data Index: 906717 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 3037203 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.6703. Min Act: -0.1700
Data Index: 856805 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 5368031 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7016. Min Act: -0.1700
Data Index: 5775408 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4516. Min Range: -6.4516
Max Act: 5.7328. Min Act: -0.1700
Data Index: 8106858 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19