Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8467. Min Range: -7.8467
Max Act: 7.8467. Min Act: -0.1700
Data Index: 3616403 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8467. Min Range: -7.8467
Max Act: 7.1905. Min Act: -0.1700
Data Index: 4528662 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8467. Min Range: -7.8467
Max Act: 7.0655. Min Act: -0.1700
Data Index: 4730837 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.9717. Min Act: -0.1700
Data Index: 1895083 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.9717. Min Act: -0.1700
Data Index: 1571204 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.9405. Min Act: -0.1700
Data Index: 5580514 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.9092. Min Act: -0.1700
Data Index: 5062224 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.9092. Min Act: -0.1700
Data Index: 7665988 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.8467. Min Act: -0.1700
Data Index: 5247625 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.8467. Min Act: -0.1700
Data Index: 7187430 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.8467. Min Act: -0.1700
Data Index: 2594582 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7842. Min Act: -0.1700
Data Index: 3527304 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.8155. Min Act: -0.1700
Data Index: 4131693 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7842. Min Act: -0.1700
Data Index: 617642 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7842. Min Act: -0.1700
Data Index: 8791896 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7842. Min Act: -0.1700
Data Index: 398449 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7530. Min Act: -0.1700
Data Index: 4683950 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7530. Min Act: -0.1700
Data Index: 8474746 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.7217. Min Act: -0.1700
Data Index: 5497638 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8467. Min Range: -7.8467
Max Act: 6.6905. Min Act: -0.1700
Data Index: 7078348 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19