Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 4121527 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 461515 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.6833. Min Act: -0.1700
Data Index: 7752123 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.6520. Min Act: -0.1700
Data Index: 8739826 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4958. Min Act: -0.1700
Data Index: 8568290 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4645. Min Act: -0.1700
Data Index: 5199302 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4958. Min Act: -0.1700
Data Index: 3128695 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4958. Min Act: -0.1700
Data Index: 1024538 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4645. Min Act: -0.1700
Data Index: 7895606 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4333. Min Act: -0.1700
Data Index: 8624026 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4020. Min Act: -0.1700
Data Index: 590463 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.4020. Min Act: -0.1700
Data Index: 6539066 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.3708. Min Act: -0.1700
Data Index: 3335222 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.3395. Min Act: -0.1700
Data Index: 4600401 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 5270873 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.3083. Min Act: -0.1700
Data Index: 8258032 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 7382950 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 3947429 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.2770. Min Act: -0.1700
Data Index: 1951229 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7770. Min Range: -5.7770
Max Act: 5.3083. Min Act: -0.1700
Data Index: 3117312 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19