Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5217 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0771. Min Range: -6.0771
Max Act: 6.0771. Min Act: -0.1700
Data Index: 8605754 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0771. Min Range: -6.0771
Max Act: 6.0146. Min Act: -0.1700
Data Index: 8605753 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.9833. Min Act: -0.1700
Data Index: 4557994 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.9208. Min Act: -0.1700
Data Index: 257144 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8896. Min Act: -0.1700
Data Index: 733032 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8896. Min Act: -0.1700
Data Index: 258935 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8583. Min Act: -0.1700
Data Index: 6263700 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8271. Min Act: -0.1700
Data Index: 5800479 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8271. Min Act: -0.1700
Data Index: 3791977 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8271. Min Act: -0.1700
Data Index: 7564743 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.8583. Min Act: -0.1700
Data Index: 4397953 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7958. Min Act: -0.1700
Data Index: 5664287 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7958. Min Act: -0.1700
Data Index: 1006493 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7646. Min Act: -0.1700
Data Index: 7949188 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7333. Min Act: -0.1700
Data Index: 1896118 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7333. Min Act: -0.1700
Data Index: 416189 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7333. Min Act: -0.1700
Data Index: 7150397 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7021. Min Act: -0.1700
Data Index: 842749 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.6708. Min Act: -0.1700
Data Index: 3941268 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0771. Min Range: -6.0771
Max Act: 5.7021. Min Act: -0.1700
Data Index: 6773185 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19