Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0437. Min Range: -8.0437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 1065287 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0437. Min Range: -8.0437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 5986797 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.9187. Min Act: -0.1700
Data Index: 8137395 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.8562. Min Act: -0.1700
Data Index: 6966190 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.8562. Min Act: -0.1700
Data Index: 7587679 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.8562. Min Act: -0.1700
Data Index: 7724434 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.8562. Min Act: -0.1700
Data Index: 4580497 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.8562. Min Act: -0.1700
Data Index: 8203464 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.8562. Min Act: -0.1700
Data Index: 8202138 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.9187. Min Act: -0.1700
Data Index: 6096761 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.7937. Min Act: -0.1700
Data Index: 6377462 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.7312. Min Act: -0.1700
Data Index: 5687025 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.7312. Min Act: -0.1700
Data Index: 3190117 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.7312. Min Act: -0.1700
Data Index: 5698501 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.6687. Min Act: -0.1700
Data Index: 8059609 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.6687. Min Act: -0.1700
Data Index: 5271856 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.6687. Min Act: -0.1700
Data Index: 792023 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.6687. Min Act: -0.1700
Data Index: 2597134 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.6687. Min Act: -0.1700
Data Index: 1814906 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0437. Min Range: -8.0437
Max Act: 7.6687. Min Act: -0.1700
Data Index: 4484136 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19