Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3736. Min Act: -0.1492
Data Index: 3429279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3559. Min Act: -0.1697
Data Index: 7348470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3383. Min Act: -0.1691
Data Index: 4749442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3295. Min Act: -0.1558
Data Index: 8421791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3295. Min Act: -0.1467
Data Index: 978642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3206. Min Act: -0.1700
Data Index: 2336149 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3206. Min Act: -0.1699
Data Index: 72508 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.3118. Min Act: -0.1699
Data Index: 2364538 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2942. Min Act: -0.1692
Data Index: 6425774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2942. Min Act: -0.1382
Data Index: 4372556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2854. Min Act: -0.1585
Data Index: 1374072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2765. Min Act: -0.1681
Data Index: 3848083 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2942. Min Act: -0.1699
Data Index: 4433279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2765. Min Act: -0.1390
Data Index: 5942346 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2765. Min Act: -0.1700
Data Index: 6460850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2854. Min Act: -0.1684
Data Index: 5723098 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2765. Min Act: -0.1695
Data Index: 4651866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2677. Min Act: -0.1602
Data Index: 4535441 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2677. Min Act: -0.1492
Data Index: 4084581 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3736. Min Range: -1.3736
Max Act: 1.2677. Min Act: -0.1700
Data Index: 7080207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19