Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3801 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4741. Min Range: -7.4741
Max Act: 7.4741. Min Act: -0.1700
Data Index: 7526579 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4741. Min Range: -7.4741
Max Act: 7.2553. Min Act: -0.1700
Data Index: 3079411 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4741. Min Range: -7.4741
Max Act: 7.1303. Min Act: -0.1700
Data Index: 7105138 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4741. Min Range: -7.4741
Max Act: 7.1303. Min Act: -0.1700
Data Index: 7665298 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4741. Min Range: -7.4741
Max Act: 7.0678. Min Act: -0.1700
Data Index: 5429819 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4741. Min Range: -7.4741
Max Act: 7.0366. Min Act: -0.1700
Data Index: 6119207 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.9741. Min Act: -0.1700
Data Index: 8622446 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.9741. Min Act: -0.1700
Data Index: 7477854 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.9428. Min Act: -0.1700
Data Index: 8476568 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.9116. Min Act: -0.1700
Data Index: 7067484 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8803. Min Act: -0.1700
Data Index: 8787802 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8803. Min Act: -0.1700
Data Index: 7986418 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8803. Min Act: -0.1700
Data Index: 298627 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8803. Min Act: -0.1700
Data Index: 3893659 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8491. Min Act: -0.1700
Data Index: 6865964 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8491. Min Act: -0.1700
Data Index: 5421465 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8491. Min Act: -0.1700
Data Index: 2610109 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8178. Min Act: -0.1700
Data Index: 7796219 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.8178. Min Act: -0.1700
Data Index: 5157731 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4741. Min Range: -7.4741
Max Act: 6.7866. Min Act: -0.1700
Data Index: 6967198 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19