Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0944. Min Range: -8.0944
Max Act: 8.0944. Min Act: -0.1700
Data Index: 3842362 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.8757. Min Act: -0.1700
Data Index: 4285379 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.8757. Min Act: -0.1700
Data Index: 7944341 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.6569. Min Act: -0.1700
Data Index: 6009721 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.6257. Min Act: -0.1700
Data Index: 5900477 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.7507. Min Act: -0.1700
Data Index: 12881 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.5944. Min Act: -0.1700
Data Index: 443954 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.6257. Min Act: -0.1700
Data Index: 7547498 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.6257. Min Act: -0.1700
Data Index: 2498940 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.5319. Min Act: -0.1700
Data Index: 4694328 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.5319. Min Act: -0.1700
Data Index: 2968324 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.4382. Min Act: -0.1700
Data Index: 5470949 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.4069. Min Act: -0.1700
Data Index: 4034596 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.4694. Min Act: -0.1700
Data Index: 5605541 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.4069. Min Act: -0.1700
Data Index: 6230136 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.3132. Min Act: -0.1700
Data Index: 8761761 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.3132. Min Act: -0.1700
Data Index: 1186948 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.3757. Min Act: -0.1700
Data Index: 7517623 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.3444. Min Act: -0.1700
Data Index: 7147801 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0944. Min Range: -8.0944
Max Act: 7.3132. Min Act: -0.1700
Data Index: 5354385 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19