Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 77 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0856. Min Range: -11.0856
Max Act: 11.0856. Min Act: -0.1700
Data Index: 7122836 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0856. Min Range: -11.0856
Max Act: 11.0231. Min Act: -0.1700
Data Index: 5273489 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.7731. Min Act: -0.1700
Data Index: 1265549 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.8356. Min Act: -0.1700
Data Index: 420902 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.8356. Min Act: -0.1700
Data Index: 243109 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.8356. Min Act: -0.1700
Data Index: 901605 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.7106. Min Act: -0.1700
Data Index: 736568 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.7106. Min Act: -0.1700
Data Index: 2432674 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.7731. Min Act: -0.1700
Data Index: 5334783 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.7106. Min Act: -0.1700
Data Index: 1504504 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.6481. Min Act: -0.1700
Data Index: 740934 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.5856. Min Act: -0.1700
Data Index: 812372 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.5856. Min Act: -0.1700
Data Index: 1384124 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.4606. Min Act: -0.1700
Data Index: 5609034 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.5231. Min Act: -0.1700
Data Index: 5799722 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.4606. Min Act: -0.1700
Data Index: 2722981 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.4606. Min Act: -0.1700
Data Index: 6735189 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.4606. Min Act: -0.1700
Data Index: 1741435 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.4606. Min Act: -0.1700
Data Index: 3875477 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0856. Min Range: -11.0856
Max Act: 10.4606. Min Act: -0.1700
Data Index: 4998583 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19