Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.3709. Min Act: -0.1700
Data Index: 8328331 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.3397. Min Act: -0.1700
Data Index: 5245317 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.2459. Min Act: -0.1700
Data Index: 6029832 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.2147. Min Act: -0.1700
Data Index: 8695568 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.2147. Min Act: -0.1700
Data Index: 5234422 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.1834. Min Act: -0.1700
Data Index: 542914 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.1522. Min Act: -0.1700
Data Index: 937615 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.1522. Min Act: -0.1700
Data Index: 3005306 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.0897. Min Act: -0.1700
Data Index: 1327551 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.0272. Min Act: -0.1700
Data Index: 4701567 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.0584. Min Act: -0.1700
Data Index: 3055589 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6768642 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3709. Min Range: -6.3709
Max Act: 6.0584. Min Act: -0.1700
Data Index: 522975 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9959. Min Act: -0.1700
Data Index: 7896232 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9647. Min Act: -0.1700
Data Index: 5596162 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9334. Min Act: -0.1700
Data Index: 3370758 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9022. Min Act: -0.1700
Data Index: 6418569 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9334. Min Act: -0.1700
Data Index: 7002304 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9334. Min Act: -0.1700
Data Index: 4798222 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3709. Min Range: -6.3709
Max Act: 5.9334. Min Act: -0.1700
Data Index: 3177887 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19