Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0138. Min Range: -5.0138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 1852068 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.8576. Min Act: -0.1700
Data Index: 192876 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.7951. Min Act: -0.1700
Data Index: 3733286 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.7951. Min Act: -0.1700
Data Index: 6056905 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.7951. Min Act: -0.1700
Data Index: 8046398 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.7638. Min Act: -0.1700
Data Index: 3673891 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.7326. Min Act: -0.1700
Data Index: 1718810 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.7013. Min Act: -0.1700
Data Index: 1729991 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6701. Min Act: -0.1700
Data Index: 5415229 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6701. Min Act: -0.1700
Data Index: 477570 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6701. Min Act: -0.1700
Data Index: 22498 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6388. Min Act: -0.1700
Data Index: 5637436 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6388. Min Act: -0.1700
Data Index: 8465592 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6388. Min Act: -0.1700
Data Index: 3097571 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6076. Min Act: -0.1700
Data Index: 8729649 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6388. Min Act: -0.1700
Data Index: 3559620 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.5763. Min Act: -0.1700
Data Index: 182660 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6076. Min Act: -0.1700
Data Index: 182662 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.6076. Min Act: -0.1700
Data Index: 4172197 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0138. Min Range: -5.0138
Max Act: 4.5763. Min Act: -0.1700
Data Index: 6806483 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19