Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.9128. Min Act: -0.1700
Data Index: 2918733 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.7878. Min Act: -0.1700
Data Index: 5838887 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.7253. Min Act: -0.1700
Data Index: 8676400 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.3816. Min Act: -0.1700
Data Index: 1604312 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.3816. Min Act: -0.1700
Data Index: 3921802 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.3816. Min Act: -0.1700
Data Index: 3107100 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 249294 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.2878. Min Act: -0.1700
Data Index: 341094 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.2566. Min Act: -0.1700
Data Index: 2701789 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.2566. Min Act: -0.1700
Data Index: 4774749 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1941. Min Act: -0.1700
Data Index: 7825260 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1628. Min Act: -0.1700
Data Index: 1822285 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1628. Min Act: -0.1700
Data Index: 6968003 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1316. Min Act: -0.1700
Data Index: 524757 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1003. Min Act: -0.1700
Data Index: 1259175 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1003. Min Act: -0.1700
Data Index: 3500118 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.0691. Min Act: -0.1700
Data Index: 294508 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1003. Min Act: -0.1700
Data Index: 5148796 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1316. Min Act: -0.1700
Data Index: 3644316 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9128. Min Range: -5.9128
Max Act: 5.1316. Min Act: -0.1700
Data Index: 1182562 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19