Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1761 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8749. Min Range: -12.8749
Max Act: 12.8749. Min Act: -0.1700
Data Index: 6619406 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8749. Min Range: -12.8749
Max Act: 12.2499. Min Act: -0.1700
Data Index: 4598611 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8749. Min Range: -12.8749
Max Act: 12.0624. Min Act: -0.1700
Data Index: 4218711 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8749. Min Range: -12.8749
Max Act: 12.1249. Min Act: -0.1700
Data Index: 8378640 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8749. Min Range: -12.8749
Max Act: 12.0624. Min Act: -0.1700
Data Index: 8819391 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8749. Min Act: -0.1700
Data Index: 3516362 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8124. Min Act: -0.1700
Data Index: 3818354 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8749. Min Act: -0.1700
Data Index: 8023886 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8749. Min Act: -0.1700
Data Index: 5762541 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8124. Min Act: -0.1700
Data Index: 7617564 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8124. Min Act: -0.1700
Data Index: 1059918 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.8124. Min Act: -0.1700
Data Index: 785244 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.7499. Min Act: -0.1700
Data Index: 1467328 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.7499. Min Act: -0.1700
Data Index: 463599 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.7499. Min Act: -0.1700
Data Index: 4716509 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.6874. Min Act: -0.1700
Data Index: 2911849 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.6874. Min Act: -0.1700
Data Index: 3848754 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.6874. Min Act: -0.1700
Data Index: 1221892 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.6874. Min Act: -0.1700
Data Index: 510165 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8749. Min Range: -12.8749
Max Act: 11.6249. Min Act: -0.1700
Data Index: 392097 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19