Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.3399. Min Act: -0.1700
Data Index: 487666 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.2143. Min Act: -0.1700
Data Index: 4445833 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.2300. Min Act: -0.1700
Data Index: 7110543 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1513. Min Act: -0.1700
Data Index: 7341880 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1513. Min Act: -0.1700
Data Index: 4484456 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1199. Min Act: -0.1700
Data Index: 1562644 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1199. Min Act: -0.1700
Data Index: 1212401 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1356. Min Act: -0.1700
Data Index: 3224391 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1041. Min Act: -0.1700
Data Index: 4443213 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1199. Min Act: -0.1700
Data Index: 4511114 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.1041. Min Act: -0.1700
Data Index: 1742488 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0883. Min Act: -0.1700
Data Index: 2030446 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0883. Min Act: -0.1700
Data Index: 3441295 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0726. Min Act: -0.1700
Data Index: 8062059 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0568. Min Act: -0.1700
Data Index: 6703482 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0568. Min Act: -0.1700
Data Index: 2224884 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0568. Min Act: -0.1700
Data Index: 5728316 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0568. Min Act: -0.1700
Data Index: 1408174 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0726. Min Act: -0.1700
Data Index: 2499229 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3399. Min Range: -3.3399
Max Act: 3.0883. Min Act: -0.1700
Data Index: 5345774 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19