Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 100 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.8369. Min Act: -0.1700
Data Index: 362758 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.7431. Min Act: -0.1700
Data Index: 830027 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.7119. Min Act: -0.1700
Data Index: 4910290 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 5055821 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 5834075 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 7871899 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.6181. Min Act: -0.1700
Data Index: 7843726 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.5869. Min Act: -0.1700
Data Index: 2650093 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.5869. Min Act: -0.1700
Data Index: 7506977 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.5556. Min Act: -0.1700
Data Index: 2597847 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.5869. Min Act: -0.1700
Data Index: 5349128 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4931. Min Act: -0.1700
Data Index: 5565229 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4931. Min Act: -0.1700
Data Index: 7299255 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4931. Min Act: -0.1700
Data Index: 636066 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4619. Min Act: -0.1700
Data Index: 6085887 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4619. Min Act: -0.1700
Data Index: 2752871 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4306. Min Act: -0.1700
Data Index: 480934 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.4306. Min Act: -0.1700
Data Index: 1891272 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.3681. Min Act: -0.1700
Data Index: 3893937 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8369. Min Range: -5.8369
Max Act: 5.3681. Min Act: -0.1700
Data Index: 8523678 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19