Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4100 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.4752. Min Act: -0.1700
Data Index: 2134486 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.4752. Min Act: -0.1700
Data Index: 2050985 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.4440. Min Act: -0.1700
Data Index: 5408308 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.4127. Min Act: -0.1700
Data Index: 1807758 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.3502. Min Act: -0.1700
Data Index: 4612038 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.3190. Min Act: -0.1700
Data Index: 2230269 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2877. Min Act: -0.1700
Data Index: 7423839 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2877. Min Act: -0.1700
Data Index: 906559 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2877. Min Act: -0.1700
Data Index: 6567044 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2565. Min Act: -0.1700
Data Index: 4944328 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2565. Min Act: -0.1700
Data Index: 7620655 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2565. Min Act: -0.1700
Data Index: 6536828 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2877. Min Act: -0.1700
Data Index: 7035117 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2565. Min Act: -0.1700
Data Index: 4652672 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2565. Min Act: -0.1700
Data Index: 6677806 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2252. Min Act: -0.1700
Data Index: 2359510 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2252. Min Act: -0.1700
Data Index: 7404094 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2252. Min Act: -0.1700
Data Index: 8201488 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2252. Min Act: -0.1700
Data Index: 8280734 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4752. Min Range: -6.4752
Max Act: 6.2565. Min Act: -0.1700
Data Index: 5533128 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19