Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2298 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.8932. Min Act: -0.1700
Data Index: 4509115 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.8932. Min Act: -0.1700
Data Index: 4750352 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7978. Min Act: -0.1700
Data Index: 2771955 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.8137. Min Act: -0.1700
Data Index: 3411112 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7819. Min Act: -0.1700
Data Index: 3667938 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7659. Min Act: -0.1700
Data Index: 7090510 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7340. Min Act: -0.1700
Data Index: 4203333 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7340. Min Act: -0.1700
Data Index: 706385 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7180. Min Act: -0.1700
Data Index: 260885 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7340. Min Act: -0.1700
Data Index: 3919323 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7020. Min Act: -0.1700
Data Index: 6092238 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7180. Min Act: -0.1700
Data Index: 3850403 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7020. Min Act: -0.1700
Data Index: 3186701 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7180. Min Act: -0.1700
Data Index: 4567530 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.6700. Min Act: -0.1700
Data Index: 3987402 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.6700. Min Act: -0.1700
Data Index: 5810131 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.6700. Min Act: -0.1700
Data Index: 2816900 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.6860. Min Act: -0.1700
Data Index: 8820403 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.7020. Min Act: -0.1700
Data Index: 4610013 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8932. Min Range: -2.8932
Max Act: 2.6860. Min Act: -0.1700
Data Index: 1651123 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19