Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.8020. Min Act: -0.1700
Data Index: 6222016 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.6145. Min Act: -0.1700
Data Index: 4230134 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.6145. Min Act: -0.1700
Data Index: 6154341 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.3020. Min Act: -0.1700
Data Index: 3724019 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.1770. Min Act: -0.1700
Data Index: 3755452 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.2395. Min Act: -0.1700
Data Index: 1272083 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.0520. Min Act: -0.1700
Data Index: 4615435 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.1770. Min Act: -0.1700
Data Index: 1980668 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.5520. Min Act: -0.1700
Data Index: 5005980 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.7395. Min Act: -0.1700
Data Index: 1783171 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.8645. Min Act: -0.1700
Data Index: 7867905 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.9270. Min Act: -0.1700
Data Index: 4930489 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.8020. Min Act: -0.1700
Data Index: 5800343 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8020. Min Range: -10.8020
Max Act: 7.6145. Min Act: -0.1700
Data Index: 3068921 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.1145. Min Act: -0.1700
Data Index: 4496363 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8020. Min Range: -10.8020
Max Act: 10.0520. Min Act: -0.1700
Data Index: 13943 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.4270. Min Act: -0.1700
Data Index: 4176832 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8020. Min Range: -10.8020
Max Act: 8.1145. Min Act: -0.1700
Data Index: 8370338 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.3645. Min Act: -0.1700
Data Index: 4915788 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8020. Min Range: -10.8020
Max Act: 9.3645. Min Act: -0.1700
Data Index: 8568520 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19