Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.8559. Min Act: -0.1700
Data Index: 8803288 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.6996. Min Act: -0.1700
Data Index: 4879643 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.6059. Min Act: -0.1700
Data Index: 7321023 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.6059. Min Act: -0.1700
Data Index: 8199017 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5746. Min Act: -0.1700
Data Index: 4488401 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5434. Min Act: -0.1700
Data Index: 6309677 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5434. Min Act: -0.1700
Data Index: 4659238 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5121. Min Act: -0.1700
Data Index: 773922 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5121. Min Act: -0.1700
Data Index: 4493639 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5121. Min Act: -0.1700
Data Index: 315262 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.5121. Min Act: -0.1700
Data Index: 5301378 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.4809. Min Act: -0.1700
Data Index: 4783943 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.4496. Min Act: -0.1700
Data Index: 7740571 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.4496. Min Act: -0.1700
Data Index: 7175442 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.4809. Min Act: -0.1700
Data Index: 5597411 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.4496. Min Act: -0.1700
Data Index: 1052215 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.3871. Min Act: -0.1700
Data Index: 8444125 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.3871. Min Act: -0.1700
Data Index: 7375352 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.3871. Min Act: -0.1700
Data Index: 1499293 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8559. Min Range: -5.8559
Max Act: 5.3559. Min Act: -0.1700
Data Index: 5263498 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19