Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.3941. Min Act: -0.1700
Data Index: 7078354 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.1441. Min Act: -0.1700
Data Index: 7944733 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.2066. Min Act: -0.1700
Data Index: 3557797 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.0816. Min Act: -0.1700
Data Index: 131374 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.0191. Min Act: -0.1700
Data Index: 3151262 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.0191. Min Act: -0.1700
Data Index: 6628588 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.9566. Min Act: -0.1700
Data Index: 2830805 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.9566. Min Act: -0.1700
Data Index: 7238156 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3941. Min Range: -10.3941
Max Act: 10.0191. Min Act: -0.1700
Data Index: 8152478 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.8941. Min Act: -0.1700
Data Index: 1202303 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.8316. Min Act: -0.1700
Data Index: 4834724 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7691. Min Act: -0.1700
Data Index: 7055061 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7691. Min Act: -0.1700
Data Index: 3652568 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7691. Min Act: -0.1700
Data Index: 1200310 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7691. Min Act: -0.1700
Data Index: 2301571 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7066. Min Act: -0.1700
Data Index: 7561298 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.6441. Min Act: -0.1700
Data Index: 4404081 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7066. Min Act: -0.1700
Data Index: 5378071 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.7066. Min Act: -0.1700
Data Index: 6376321 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3941. Min Range: -10.3941
Max Act: 9.6441. Min Act: -0.1700
Data Index: 4125980 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19