Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.5287. Min Act: -0.1700
Data Index: 6367919 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.4975. Min Act: -0.1700
Data Index: 7730275 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.3412. Min Act: -0.1700
Data Index: 5713995 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.2475. Min Act: -0.1700
Data Index: 707343 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.1850. Min Act: -0.1700
Data Index: 6250374 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.1537. Min Act: -0.1700
Data Index: 7520432 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.1537. Min Act: -0.1700
Data Index: 288398 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.0600. Min Act: -0.1700
Data Index: 6633598 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5287. Min Range: -7.5287
Max Act: 7.0600. Min Act: -0.1700
Data Index: 6574876 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9975. Min Act: -0.1700
Data Index: 5049853 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9975. Min Act: -0.1700
Data Index: 3424892 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9662. Min Act: -0.1700
Data Index: 4611360 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9975. Min Act: -0.1700
Data Index: 626384 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9662. Min Act: -0.1700
Data Index: 5633065 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9662. Min Act: -0.1700
Data Index: 1275214 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9037. Min Act: -0.1700
Data Index: 1584790 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9350. Min Act: -0.1700
Data Index: 4642896 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9037. Min Act: -0.1700
Data Index: 3786922 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.9037. Min Act: -0.1700
Data Index: 7165590 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5287. Min Range: -7.5287
Max Act: 6.8412. Min Act: -0.1700
Data Index: 328535 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19