Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 482 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0580. Min Range: -7.0580
Max Act: 7.0580. Min Act: -0.1700
Data Index: 1468982 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0580. Min Range: -7.0580
Max Act: 7.0268. Min Act: -0.1700
Data Index: 392325 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.9643. Min Act: -0.1700
Data Index: 6860011 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.9330. Min Act: -0.1700
Data Index: 1676890 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.9018. Min Act: -0.1700
Data Index: 5022660 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.9018. Min Act: -0.1700
Data Index: 102459 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.8705. Min Act: -0.1700
Data Index: 1309690 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.8705. Min Act: -0.1700
Data Index: 6294069 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.8705. Min Act: -0.1699
Data Index: 8417779 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.8393. Min Act: -0.1700
Data Index: 6813198 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.8080. Min Act: -0.1700
Data Index: 5806169 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.7455. Min Act: -0.1700
Data Index: 2225980 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.7143. Min Act: -0.1700
Data Index: 4302475 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.6830. Min Act: -0.1700
Data Index: 1357036 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.7143. Min Act: -0.1700
Data Index: 8417781 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.7143. Min Act: -0.1700
Data Index: 646096 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.6830. Min Act: -0.1700
Data Index: 1854867 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.6830. Min Act: -0.1700
Data Index: 1720930 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.6518. Min Act: -0.1700
Data Index: 720593 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0580. Min Range: -7.0580
Max Act: 6.6518. Min Act: -0.1700
Data Index: 5404640 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19