Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.7593. Min Act: -0.1700
Data Index: 4935935 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.6343. Min Act: -0.1700
Data Index: 4473715 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.5718. Min Act: -0.1700
Data Index: 2717104 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.3843. Min Act: -0.1700
Data Index: 4070436 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.2593. Min Act: -0.1700
Data Index: 1659638 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.0718. Min Act: -0.1700
Data Index: 7929562 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.0718. Min Act: -0.1700
Data Index: 8041872 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.0718. Min Act: -0.1700
Data Index: 4204378 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7593. Min Range: -10.7593
Max Act: 10.0093. Min Act: -0.1700
Data Index: 2852837 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.9468. Min Act: -0.1700
Data Index: 6056370 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.8843. Min Act: -0.1700
Data Index: 1602965 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.8843. Min Act: -0.1700
Data Index: 8655698 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.8218. Min Act: -0.1700
Data Index: 8655699 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.8218. Min Act: -0.1700
Data Index: 5682261 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.8218. Min Act: -0.1700
Data Index: 2443863 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.7593. Min Act: -0.1700
Data Index: 7401715 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.7593. Min Act: -0.1700
Data Index: 4756817 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.7593. Min Act: -0.1700
Data Index: 1907833 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.6968. Min Act: -0.1700
Data Index: 8059954 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7593. Min Range: -10.7593
Max Act: 9.6968. Min Act: -0.1700
Data Index: 2933509 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19