Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6037 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3002. Min Range: -8.3002
Max Act: 8.3002. Min Act: -0.1700
Data Index: 8052053 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3002. Min Range: -8.3002
Max Act: 8.1752. Min Act: -0.1700
Data Index: 3203404 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3002. Min Range: -8.3002
Max Act: 8.1127. Min Act: -0.1700
Data Index: 4955731 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3002. Min Range: -8.3002
Max Act: 8.0502. Min Act: -0.1700
Data Index: 6075224 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.9252. Min Act: -0.1700
Data Index: 7956297 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.8627. Min Act: -0.1700
Data Index: 2259565 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.8627. Min Act: -0.1700
Data Index: 2485335 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.7377. Min Act: -0.1700
Data Index: 5033656 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.7377. Min Act: -0.1700
Data Index: 1533044 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.7377. Min Act: -0.1700
Data Index: 7108797 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6752. Min Act: -0.1700
Data Index: 3080634 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6752. Min Act: -0.1700
Data Index: 2923103 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6752. Min Act: -0.1700
Data Index: 827088 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6439. Min Act: -0.1700
Data Index: 5908720 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6127. Min Act: -0.1700
Data Index: 7475242 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6127. Min Act: -0.1700
Data Index: 198285 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6127. Min Act: -0.1700
Data Index: 550259 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.6439. Min Act: -0.1700
Data Index: 2647968 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.5814. Min Act: -0.1700
Data Index: 3490437 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3002. Min Range: -8.3002
Max Act: 7.5814. Min Act: -0.1700
Data Index: 8175251 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19