Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6214 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.4708. Min Act: -0.1700
Data Index: 4238286 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.3770. Min Act: -0.1700
Data Index: 5768985 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.3145. Min Act: -0.1700
Data Index: 7619192 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.2833. Min Act: -0.1700
Data Index: 3058946 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.2208. Min Act: -0.1700
Data Index: 5212709 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1895. Min Act: -0.1700
Data Index: 2222806 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1270. Min Act: -0.1700
Data Index: 906347 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1270. Min Act: -0.1700
Data Index: 4916116 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1270. Min Act: -0.1700
Data Index: 7532625 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0958. Min Act: -0.1700
Data Index: 5079379 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0645. Min Act: -0.1700
Data Index: 3783266 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 3623042 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0645. Min Act: -0.1700
Data Index: 4266407 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0645. Min Act: -0.1700
Data Index: 848340 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 2817002 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 4525444 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 8591042 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 2342851 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 1062084 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0020. Min Act: -0.1700
Data Index: 547640 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19