Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4219 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0669. Min Range: -9.0669
Max Act: 9.0669. Min Act: -0.1700
Data Index: 7272320 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0669. Min Range: -9.0669
Max Act: 9.0044. Min Act: -0.1700
Data Index: 3550872 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.8169. Min Act: -0.1700
Data Index: 4833240 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.6919. Min Act: -0.1700
Data Index: 168104 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.4419. Min Act: -0.1700
Data Index: 3842723 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.3794. Min Act: -0.1700
Data Index: 1102116 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.3794. Min Act: -0.1700
Data Index: 1306268 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.3794. Min Act: -0.1700
Data Index: 3591401 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.3169. Min Act: -0.1700
Data Index: 2464543 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.3169. Min Act: -0.1700
Data Index: 2097269 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.3794. Min Act: -0.1700
Data Index: 7003713 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.2544. Min Act: -0.1700
Data Index: 3465066 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.2544. Min Act: -0.1700
Data Index: 7832953 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.1919. Min Act: -0.1700
Data Index: 7123321 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.1919. Min Act: -0.1700
Data Index: 3355946 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.1919. Min Act: -0.1700
Data Index: 6468396 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.2544. Min Act: -0.1700
Data Index: 291693 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.1294. Min Act: -0.1700
Data Index: 455978 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.1294. Min Act: -0.1700
Data Index: 3406565 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0669. Min Range: -9.0669
Max Act: 8.0669. Min Act: -0.1700
Data Index: 5386326 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19