Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.5298. Min Act: -0.1700
Data Index: 6309960 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4859. Min Act: -0.1700
Data Index: 3752222 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4771. Min Act: -0.1700
Data Index: 6253110 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4771. Min Act: -0.1700
Data Index: 4346973 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4508. Min Act: -0.1700
Data Index: 980040 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4508. Min Act: -0.1700
Data Index: 7652783 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4508. Min Act: -0.1700
Data Index: 3841962 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4508. Min Act: -0.1700
Data Index: 2437409 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4508. Min Act: -0.1700
Data Index: 3786178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4420. Min Act: -0.1695
Data Index: 1019141 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4332. Min Act: -0.1700
Data Index: 8508636 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4332. Min Act: -0.1700
Data Index: 2168351 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4332. Min Act: -0.1700
Data Index: 7207904 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4244. Min Act: -0.1700
Data Index: 4590173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4156. Min Act: -0.1700
Data Index: 5680105 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4156. Min Act: -0.1700
Data Index: 5598031 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4156. Min Act: -0.1700
Data Index: 5292821 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4156. Min Act: -0.1700
Data Index: 1728009 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4067. Min Act: -0.1700
Data Index: 5637013 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5298. Min Range: -1.5298
Max Act: 1.4067. Min Act: -0.1700
Data Index: 4979324 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19