Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.5395. Min Act: -0.1700
Data Index: 8552562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.5132. Min Act: -0.1700
Data Index: 2721591 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4868. Min Act: -0.1700
Data Index: 4789781 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4780. Min Act: -0.1700
Data Index: 2235804 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4780. Min Act: -0.1700
Data Index: 5143228 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4780. Min Act: -0.1700
Data Index: 5456001 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4693. Min Act: -0.1700
Data Index: 6564844 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4780. Min Act: -0.1700
Data Index: 6028923 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4780. Min Act: -0.1699
Data Index: 3204712 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4693. Min Act: -0.1700
Data Index: 1384022 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4693. Min Act: -0.1700
Data Index: 3902647 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1700
Data Index: 5103085 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1700
Data Index: 5292830 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1700
Data Index: 498070 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1700
Data Index: 5984062 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4517. Min Act: -0.1698
Data Index: 3671028 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1700
Data Index: 3953040 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4517. Min Act: -0.1700
Data Index: 7598850 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1697
Data Index: 5695164 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5395. Min Range: -1.5395
Max Act: 1.4605. Min Act: -0.1700
Data Index: 870147 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19