Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.5168. Min Act: -0.1700
Data Index: 3379511 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.5480. Min Act: -0.1700
Data Index: 2938673 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.5168. Min Act: -0.1700
Data Index: 7749917 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.4230. Min Act: -0.1700
Data Index: 4616392 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.3918. Min Act: -0.1700
Data Index: 7050395 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.3605. Min Act: -0.1700
Data Index: 7755112 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.3292. Min Act: -0.1700
Data Index: 4644351 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2980. Min Act: -0.1700
Data Index: 6716552 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2667. Min Act: -0.1700
Data Index: 7619262 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2667. Min Act: -0.1700
Data Index: 3247893 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2667. Min Act: -0.1700
Data Index: 3644154 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2355. Min Act: -0.1700
Data Index: 3408406 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2355. Min Act: -0.1700
Data Index: 7420512 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2355. Min Act: -0.1700
Data Index: 3611813 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2042. Min Act: -0.1700
Data Index: 8611533 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2042. Min Act: -0.1700
Data Index: 7343696 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2042. Min Act: -0.1700
Data Index: 5675099 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.1730. Min Act: -0.1700
Data Index: 3039512 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.2042. Min Act: -0.1700
Data Index: 5109113 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5480. Min Range: -4.5480
Max Act: 4.1417. Min Act: -0.1700
Data Index: 6939153 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19