Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.4309. Min Act: -0.1700
Data Index: 127268 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3996. Min Act: -0.1700
Data Index: 5319940 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3996. Min Act: -0.1700
Data Index: 248603 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3996. Min Act: -0.1700
Data Index: 4605586 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3996. Min Act: -0.1700
Data Index: 6184901 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3684. Min Act: -0.1700
Data Index: 5545444 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3684. Min Act: -0.1700
Data Index: 7875503 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3684. Min Act: -0.1700
Data Index: 5924495 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3684. Min Act: -0.1700
Data Index: 4483773 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 8271 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 2082506 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 1825280 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 6230031 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 8068679 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 4028616 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 7510388 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 1265493 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3371. Min Act: -0.1700
Data Index: 7233278 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3059. Min Act: -0.1700
Data Index: 6954229 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4309. Min Range: -4.4309
Max Act: 4.3059. Min Act: -0.1700
Data Index: 5131567 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19