Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5408. Min Act: -0.1700
Data Index: 4884428 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5095. Min Act: -0.1700
Data Index: 2485300 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5095. Min Act: -0.1700
Data Index: 1559849 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4783. Min Act: -0.1700
Data Index: 1691719 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5095. Min Act: -0.1700
Data Index: 8779837 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 6488390 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5095. Min Act: -0.1700
Data Index: 4684733 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4783. Min Act: -0.1700
Data Index: 7677691 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 3414684 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 5281256 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4158. Min Act: -0.1700
Data Index: 7423222 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 1453164 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 8093740 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3533. Min Act: -0.1700
Data Index: 7477546 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 4525451 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3220. Min Act: -0.1700
Data Index: 6691943 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3220. Min Act: -0.1700
Data Index: 4823451 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3220. Min Act: -0.1700
Data Index: 7026541 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3220. Min Act: -0.1700
Data Index: 5563055 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.2907. Min Act: -0.1700
Data Index: 1262020 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19