Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6352 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.5571. Min Act: -0.1700
Data Index: 8759555 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.5258. Min Act: -0.1700
Data Index: 2392006 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.4633. Min Act: -0.1700
Data Index: 1934363 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.4321. Min Act: -0.1700
Data Index: 1817285 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.4008. Min Act: -0.1700
Data Index: 1169020 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3696. Min Act: -0.1700
Data Index: 8481020 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.4008. Min Act: -0.1700
Data Index: 7513076 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3696. Min Act: -0.1700
Data Index: 6753747 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3383. Min Act: -0.1700
Data Index: 4927528 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3696. Min Act: -0.1700
Data Index: 7037224 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3383. Min Act: -0.1700
Data Index: 3084292 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3383. Min Act: -0.1700
Data Index: 1821002 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3070. Min Act: -0.1700
Data Index: 5826561 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3070. Min Act: -0.1700
Data Index: 4116923 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3070. Min Act: -0.1700
Data Index: 2299394 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5549539 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.2758. Min Act: -0.1700
Data Index: 45495 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.3070. Min Act: -0.1700
Data Index: 3731646 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5051615 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5571. Min Range: -4.5571
Max Act: 4.2758. Min Act: -0.1700
Data Index: 6459533 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19