Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0560. Min Range: -4.0560
Max Act: 4.0560. Min Act: -0.1700
Data Index: 3826508 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.8240. Min Act: -0.1700
Data Index: 6041929 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.8514. Min Act: -0.1700
Data Index: 5171261 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7721. Min Act: -0.1700
Data Index: 1829884 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7752. Min Act: -0.1700
Data Index: 8335966 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7929. Min Act: -0.1700
Data Index: 7163465 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7839. Min Act: -0.1700
Data Index: 2691224 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7747. Min Act: -0.1700
Data Index: 1112045 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7950. Min Act: -0.1700
Data Index: 7910413 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7739. Min Act: -0.1700
Data Index: 1343968 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7699. Min Act: -0.1700
Data Index: 5271457 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7435. Min Act: -0.1700
Data Index: 4252731 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7173. Min Act: -0.1700
Data Index: 1466539 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7260. Min Act: -0.1700
Data Index: 186285 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.7328. Min Act: -0.1700
Data Index: 4618340 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.6776. Min Act: -0.1700
Data Index: 5396199 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.6935. Min Act: -0.1700
Data Index: 2747398 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.6907. Min Act: -0.1700
Data Index: 7477062 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.6932. Min Act: -0.1700
Data Index: 5061004 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.0560. Min Range: -4.0560
Max Act: 3.6890. Min Act: -0.1700
Data Index: 6989329 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full textTruncated
Full Text #19