Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.4877. Min Act: -0.1700
Data Index: 5679281 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.4564. Min Act: -0.1700
Data Index: 7010122 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.2377. Min Act: -0.1700
Data Index: 3647454 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.1127. Min Act: -0.1700
Data Index: 4545341 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.1439. Min Act: -0.1700
Data Index: 8214572 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.0814. Min Act: -0.1700
Data Index: 8606253 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.0814. Min Act: -0.1700
Data Index: 1738927 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.0189. Min Act: -0.1700
Data Index: 5515895 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4877. Min Range: -6.4877
Max Act: 6.0189. Min Act: -0.1700
Data Index: 8266736 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9877. Min Act: -0.1700
Data Index: 783118 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9877. Min Act: -0.1700
Data Index: 51310 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9564. Min Act: -0.1700
Data Index: 79648 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9564. Min Act: -0.1700
Data Index: 2206619 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9252. Min Act: -0.1700
Data Index: 8715137 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3917839 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3799913 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.8939. Min Act: -0.1700
Data Index: 3721021 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9252. Min Act: -0.1700
Data Index: 21639 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.8939. Min Act: -0.1700
Data Index: 4993485 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4877. Min Range: -6.4877
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3097744 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19