Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.8552. Min Act: -0.1700
Data Index: 3660040 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7927. Min Act: -0.1700
Data Index: 7089000 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7927. Min Act: -0.1700
Data Index: 3012916 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7614. Min Act: -0.1700
Data Index: 7722395 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7614. Min Act: -0.1700
Data Index: 6921449 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1697
Data Index: 8632622 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 8257743 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 2435786 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 7495581 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1699
Data Index: 4931744 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 8009665 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6989. Min Act: -0.1700
Data Index: 2721146 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 7557281 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 7115853 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 7195450 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 823506 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 4157870 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6989. Min Act: -0.1700
Data Index: 7235637 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1699
Data Index: 545150 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 4643104 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19