Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5088 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0231. Min Range: -6.0231
Max Act: 6.0231. Min Act: -0.1700
Data Index: 7329108 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.8043. Min Act: -0.1700
Data Index: 377405 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.8043. Min Act: -0.1700
Data Index: 5196783 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.7731. Min Act: -0.1700
Data Index: 482642 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.7418. Min Act: -0.1700
Data Index: 3528218 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.7106. Min Act: -0.1700
Data Index: 5282618 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.7106. Min Act: -0.1700
Data Index: 6205206 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.7106. Min Act: -0.1700
Data Index: 4829500 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6793. Min Act: -0.1700
Data Index: 2187370 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6793. Min Act: -0.1700
Data Index: 2078982 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6481. Min Act: -0.1700
Data Index: 4557696 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6481. Min Act: -0.1700
Data Index: 1478991 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6481. Min Act: -0.1700
Data Index: 5024625 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6168. Min Act: -0.1700
Data Index: 6928015 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.5856. Min Act: -0.1700
Data Index: 5829628 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.6168. Min Act: -0.1700
Data Index: 8016047 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.5543. Min Act: -0.1700
Data Index: 1177437 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.5856. Min Act: -0.1700
Data Index: 452135 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.5856. Min Act: -0.1700
Data Index: 2677707 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0231. Min Range: -6.0231
Max Act: 5.5856. Min Act: -0.1700
Data Index: 437903 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19