Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4281 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0377. Min Range: -6.0377
Max Act: 6.0377. Min Act: -0.1700
Data Index: 5830207 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.8814. Min Act: -0.1700
Data Index: 4222512 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.9127. Min Act: -0.1700
Data Index: 7570401 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.7564. Min Act: -0.1700
Data Index: 5875513 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.6314. Min Act: -0.1700
Data Index: 7865183 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.6627. Min Act: -0.1700
Data Index: 6339241 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.6002. Min Act: -0.1700
Data Index: 3737755 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.6002. Min Act: -0.1700
Data Index: 2772332 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 5618464 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.5064. Min Act: -0.1700
Data Index: 3956639 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.5064. Min Act: -0.1700
Data Index: 4544553 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.5064. Min Act: -0.1700
Data Index: 2365110 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.5064. Min Act: -0.1700
Data Index: 7344290 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4752. Min Act: -0.1700
Data Index: 6212972 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4752. Min Act: -0.1700
Data Index: 8523052 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4439. Min Act: -0.1700
Data Index: 6101319 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4439. Min Act: -0.1700
Data Index: 8041593 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4439. Min Act: -0.1700
Data Index: 95463 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4439. Min Act: -0.1700
Data Index: 7425806 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0377. Min Range: -6.0377
Max Act: 5.4439. Min Act: -0.1700
Data Index: 5197969 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19