Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4888 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.4728. Min Act: -0.1700
Data Index: 4897743 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.3166. Min Act: -0.1700
Data Index: 5475688 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.2853. Min Act: -0.1700
Data Index: 599272 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.2228. Min Act: -0.1700
Data Index: 8679146 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.2228. Min Act: -0.1700
Data Index: 8390979 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.1916. Min Act: -0.1700
Data Index: 689568 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.1916. Min Act: -0.1700
Data Index: 8544117 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.1603. Min Act: -0.1700
Data Index: 2985476 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.1291. Min Act: -0.1700
Data Index: 5139344 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0978. Min Act: -0.1700
Data Index: 2078570 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.1291. Min Act: -0.1700
Data Index: 8279099 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0978. Min Act: -0.1700
Data Index: 8471725 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0978. Min Act: -0.1700
Data Index: 6751963 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0978. Min Act: -0.1700
Data Index: 5039734 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0978. Min Act: -0.1700
Data Index: 6303505 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0978. Min Act: -0.1700
Data Index: 3239397 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.1291. Min Act: -0.1700
Data Index: 3105430 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0665. Min Act: -0.1700
Data Index: 5964091 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0665. Min Act: -0.1700
Data Index: 2203067 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4728. Min Range: -4.4728
Max Act: 4.0665. Min Act: -0.1700
Data Index: 7870709 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19