Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.5380. Min Act: -0.1700
Data Index: 8494934 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.4407. Min Act: -0.1700
Data Index: 5472981 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3918. Min Act: -0.1700
Data Index: 7970072 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.4081. Min Act: -0.1700
Data Index: 5326728 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3918. Min Act: -0.1700
Data Index: 1298222 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3755. Min Act: -0.1700
Data Index: 3114766 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3755. Min Act: -0.1700
Data Index: 7970076 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3755. Min Act: -0.1700
Data Index: 5848539 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3755. Min Act: -0.1700
Data Index: 8154495 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3591. Min Act: -0.1700
Data Index: 2839729 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3591. Min Act: -0.1700
Data Index: 7061103 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 1634830 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3591. Min Act: -0.1700
Data Index: 5848538 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 2986777 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 959240 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 6768951 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 8014010 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 2439056 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3427. Min Act: -0.1700
Data Index: 4612438 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5380. Min Range: -2.5380
Max Act: 2.3263. Min Act: -0.1700
Data Index: 3990622 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19