Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2584 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.4403. Min Act: -0.1700
Data Index: 4505928 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.3933. Min Act: -0.1700
Data Index: 3456852 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.3619. Min Act: -0.1700
Data Index: 5330356 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.3306. Min Act: -0.1700
Data Index: 1801613 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2835. Min Act: -0.1700
Data Index: 7399916 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2520. Min Act: -0.1700
Data Index: 6643220 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2678. Min Act: -0.1700
Data Index: 20977 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2678. Min Act: -0.1700
Data Index: 937233 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2678. Min Act: -0.1700
Data Index: 5096978 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2363. Min Act: -0.1700
Data Index: 5076336 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2678. Min Act: -0.1700
Data Index: 869530 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2520. Min Act: -0.1700
Data Index: 6627825 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2520. Min Act: -0.1700
Data Index: 3427061 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2206. Min Act: -0.1700
Data Index: 6578751 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2206. Min Act: -0.1700
Data Index: 242254 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2363. Min Act: -0.1700
Data Index: 1156805 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2363. Min Act: -0.1700
Data Index: 201219 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2363. Min Act: -0.1700
Data Index: 154282 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2206. Min Act: -0.1700
Data Index: 644128 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4403. Min Range: -3.4403
Max Act: 3.2206. Min Act: -0.1700
Data Index: 5599091 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19