Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3944 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1426. Min Range: -3.1426
Max Act: 3.1426. Min Act: -0.1700
Data Index: 2570443 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1426. Min Range: -3.1426
Max Act: 3.0953. Min Act: -0.1700
Data Index: 2296349 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1426. Min Range: -3.1426
Max Act: 3.0480. Min Act: -0.1700
Data Index: 4184148 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1426. Min Range: -3.1426
Max Act: 3.0164. Min Act: -0.1700
Data Index: 2433561 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9690. Min Act: -0.1700
Data Index: 6165215 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9690. Min Act: -0.1700
Data Index: 5296612 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9690. Min Act: -0.1700
Data Index: 5344124 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9690. Min Act: -0.1700
Data Index: 2477127 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9532. Min Act: -0.1700
Data Index: 4440145 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9532. Min Act: -0.1700
Data Index: 3977188 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9532. Min Act: -0.1700
Data Index: 1052541 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9373. Min Act: -0.1700
Data Index: 3942791 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9057. Min Act: -0.1700
Data Index: 7976950 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9215. Min Act: -0.1700
Data Index: 5488846 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9057. Min Act: -0.1700
Data Index: 5670768 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9373. Min Act: -0.1700
Data Index: 7216954 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9057. Min Act: -0.1700
Data Index: 6402860 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9057. Min Act: -0.1700
Data Index: 4254938 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9057. Min Act: -0.1700
Data Index: 4407424 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1426. Min Range: -3.1426
Max Act: 2.9057. Min Act: -0.1700
Data Index: 7655373 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19