Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1430. Min Range: -5.1430
Max Act: 5.1430. Min Act: -0.1700
Data Index: 666161 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8930. Min Act: -0.1700
Data Index: 8710645 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8930. Min Act: -0.1700
Data Index: 301290 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8617. Min Act: -0.1700
Data Index: 625213 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8305. Min Act: -0.1700
Data Index: 8281347 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8305. Min Act: -0.1700
Data Index: 3210422 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8305. Min Act: -0.1700
Data Index: 7718048 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8305. Min Act: -0.1700
Data Index: 5053054 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.8305. Min Act: -0.1700
Data Index: 6752005 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7992. Min Act: -0.1699
Data Index: 8678584 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7992. Min Act: -0.1700
Data Index: 6460261 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7367. Min Act: -0.1700
Data Index: 1963097 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 123407 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 1552172 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 3281996 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 5381728 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 2212140 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 7185010 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 3406981 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1430. Min Range: -5.1430
Max Act: 4.7680. Min Act: -0.1700
Data Index: 3900582 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19