Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.7278. Min Act: -0.1700
Data Index: 5467202 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.6340. Min Act: -0.1700
Data Index: 1742282 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.4778. Min Act: -0.1700
Data Index: 124737 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.3528. Min Act: -0.1700
Data Index: 1600400 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.3528. Min Act: -0.1700
Data Index: 2018154 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.3215. Min Act: -0.1700
Data Index: 8481102 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.3215. Min Act: -0.1700
Data Index: 8255183 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2590. Min Act: -0.1700
Data Index: 8660049 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2590. Min Act: -0.1700
Data Index: 5800791 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2590. Min Act: -0.1700
Data Index: 148432 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2278. Min Act: -0.1700
Data Index: 3153560 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2278. Min Act: -0.1700
Data Index: 7290385 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.1965. Min Act: -0.1700
Data Index: 5533461 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2278. Min Act: -0.1700
Data Index: 6907375 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2278. Min Act: -0.1700
Data Index: 3296577 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2278. Min Act: -0.1700
Data Index: 513481 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.2278. Min Act: -0.1700
Data Index: 4390901 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.1965. Min Act: -0.1700
Data Index: 8725407 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.1965. Min Act: -0.1700
Data Index: 6819059 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7278. Min Range: -4.7278
Max Act: 4.1653. Min Act: -0.1700
Data Index: 6715383 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19