Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0231. Min Range: -5.0231
Max Act: 5.0231. Min Act: -0.1700
Data Index: 1223562 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.8669. Min Act: -0.1700
Data Index: 2216649 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.8669. Min Act: -0.1700
Data Index: 1464591 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.8356. Min Act: -0.1700
Data Index: 436057 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7731. Min Act: -0.1700
Data Index: 4127852 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7731. Min Act: -0.1700
Data Index: 367458 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7419. Min Act: -0.1700
Data Index: 8000898 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7419. Min Act: -0.1700
Data Index: 1711036 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7731. Min Act: -0.1700
Data Index: 4530827 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7106. Min Act: -0.1700
Data Index: 3175845 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7106. Min Act: -0.1700
Data Index: 1518113 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7106. Min Act: -0.1700
Data Index: 4573732 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6794. Min Act: -0.1700
Data Index: 2618871 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.7106. Min Act: -0.1700
Data Index: 6795027 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6794. Min Act: -0.1700
Data Index: 8681539 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6794. Min Act: -0.1700
Data Index: 7479135 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6794. Min Act: -0.1700
Data Index: 6063555 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6794. Min Act: -0.1700
Data Index: 4709886 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6481. Min Act: -0.1700
Data Index: 2275411 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0231. Min Range: -5.0231
Max Act: 4.6481. Min Act: -0.1700
Data Index: 1556279 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19