Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0978. Min Range: -6.0978
Max Act: 6.0978. Min Act: -0.1700
Data Index: 1527879 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0978. Min Range: -6.0978
Max Act: 6.0665. Min Act: -0.1700
Data Index: 7088284 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.9103. Min Act: -0.1700
Data Index: 6065852 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.9103. Min Act: -0.1700
Data Index: 411766 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.8790. Min Act: -0.1700
Data Index: 181643 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.8165. Min Act: -0.1700
Data Index: 3196325 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.8165. Min Act: -0.1700
Data Index: 4375678 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7540. Min Act: -0.1700
Data Index: 3825763 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7540. Min Act: -0.1700
Data Index: 6350170 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7540. Min Act: -0.1700
Data Index: 8385080 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7540. Min Act: -0.1700
Data Index: 988466 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7228. Min Act: -0.1700
Data Index: 8062146 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7228. Min Act: -0.1700
Data Index: 4515890 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7228. Min Act: -0.1700
Data Index: 895215 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6389568 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2375798 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.6915. Min Act: -0.1700
Data Index: 2669239 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.6915. Min Act: -0.1700
Data Index: 7514402 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.6915. Min Act: -0.1700
Data Index: 2246579 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0978. Min Range: -6.0978
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7776158 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19