Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1116. Min Range: -6.1116
Max Act: 6.1116. Min Act: -0.1700
Data Index: 7345560 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1116. Min Range: -6.1116
Max Act: 6.0491. Min Act: -0.1700
Data Index: 5329761 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1116. Min Range: -6.1116
Max Act: 6.0179. Min Act: -0.1700
Data Index: 2615275 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.9866. Min Act: -0.1700
Data Index: 2567861 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.9241. Min Act: -0.1700
Data Index: 7813148 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8929. Min Act: -0.1700
Data Index: 5647231 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8929. Min Act: -0.1700
Data Index: 814415 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8616. Min Act: -0.1700
Data Index: 635804 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8616. Min Act: -0.1700
Data Index: 6702295 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8304. Min Act: -0.1700
Data Index: 7914502 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8304. Min Act: -0.1700
Data Index: 5809329 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.8304. Min Act: -0.1700
Data Index: 6613271 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6122142 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6611575 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.7366. Min Act: -0.1700
Data Index: 8738344 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.7054. Min Act: -0.1700
Data Index: 3620761 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.7054. Min Act: -0.1700
Data Index: 6743565 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.6741. Min Act: -0.1700
Data Index: 8699527 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.6429. Min Act: -0.1700
Data Index: 1161099 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1116. Min Range: -6.1116
Max Act: 5.6116. Min Act: -0.1700
Data Index: 3815770 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19