Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.8017. Min Act: -0.1700
Data Index: 7798378 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.7392. Min Act: -0.1700
Data Index: 4419527 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.4267. Min Act: -0.1700
Data Index: 7461069 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.4267. Min Act: -0.1700
Data Index: 3478525 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.3017. Min Act: -0.1700
Data Index: 124373 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.2705. Min Act: -0.1700
Data Index: 4119231 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.2705. Min Act: -0.1700
Data Index: 3043101 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.3017. Min Act: -0.1700
Data Index: 6775120 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.2705. Min Act: -0.1700
Data Index: 2740912 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.3017. Min Act: -0.1700
Data Index: 5886918 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.2080. Min Act: -0.1700
Data Index: 6098042 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.2080. Min Act: -0.1700
Data Index: 904724 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1767. Min Act: -0.1700
Data Index: 3507029 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1767. Min Act: -0.1700
Data Index: 6374917 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1767. Min Act: -0.1700
Data Index: 2754113 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1767. Min Act: -0.1700
Data Index: 6703760 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1455. Min Act: -0.1700
Data Index: 1955277 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1142. Min Act: -0.1700
Data Index: 4967983 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.1142. Min Act: -0.1700
Data Index: 7402676 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8017. Min Range: -6.8017
Max Act: 6.0830. Min Act: -0.1700
Data Index: 1946349 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19