Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.8293. Min Act: -0.1700
Data Index: 7694566 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7975. Min Act: -0.1700
Data Index: 1785406 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7656. Min Act: -0.1700
Data Index: 5536346 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7496. Min Act: -0.1700
Data Index: 4601337 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7496. Min Act: -0.1700
Data Index: 4228955 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7177. Min Act: -0.1700
Data Index: 1903501 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7017. Min Act: -0.1700
Data Index: 3421500 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7017. Min Act: -0.1700
Data Index: 4228894 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6857. Min Act: -0.1700
Data Index: 2087255 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.7017. Min Act: -0.1700
Data Index: 1149561 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6857. Min Act: -0.1700
Data Index: 8268907 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6697. Min Act: -0.1700
Data Index: 8561054 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6536. Min Act: -0.1700
Data Index: 5865694 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6536. Min Act: -0.1700
Data Index: 1785405 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6536. Min Act: -0.1700
Data Index: 1758139 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6536. Min Act: -0.1700
Data Index: 3514815 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6215. Min Act: -0.1700
Data Index: 6895587 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6376. Min Act: -0.1700
Data Index: 6593138 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6376. Min Act: -0.1700
Data Index: 8045478 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8293. Min Range: -2.8293
Max Act: 2.6215. Min Act: -0.1700
Data Index: 5917074 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19