Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5626 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.8940. Min Act: -0.1700
Data Index: 1892257 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.8314. Min Act: -0.1700
Data Index: 701805 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.8002. Min Act: -0.1700
Data Index: 8670442 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.8002. Min Act: -0.1700
Data Index: 355481 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.8002. Min Act: -0.1700
Data Index: 6891396 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 7512576 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.8002. Min Act: -0.1700
Data Index: 7764319 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 4995544 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 3561307 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 8033560 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 2033838 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 7826394 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 2471610 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 6004279 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1699
Data Index: 5759404 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7689. Min Act: -0.1700
Data Index: 3302502 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7376. Min Act: -0.1700
Data Index: 1281516 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7063. Min Act: -0.1700
Data Index: 2222479 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7376. Min Act: -0.1700
Data Index: 3265496 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8940. Min Range: -3.8940
Max Act: 3.7376. Min Act: -0.1700
Data Index: 4174562 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19