Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.8652. Min Act: -0.1700
Data Index: 382133 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.8339. Min Act: -0.1700
Data Index: 6598887 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.8339. Min Act: -0.1700
Data Index: 5830471 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.8339. Min Act: -0.1700
Data Index: 1867485 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.7401. Min Act: -0.1700
Data Index: 1352908 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6932. Min Act: -0.1700
Data Index: 8424383 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6932. Min Act: -0.1700
Data Index: 1645458 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6932. Min Act: -0.1700
Data Index: 7341824 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6775. Min Act: -0.1700
Data Index: 3132303 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6775. Min Act: -0.1700
Data Index: 3785262 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6619. Min Act: -0.1700
Data Index: 3060402 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.6306. Min Act: -0.1700
Data Index: 3592147 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5993. Min Act: -0.1700
Data Index: 3793050 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5836. Min Act: -0.1700
Data Index: 5350501 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5836. Min Act: -0.1700
Data Index: 8134021 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5680. Min Act: -0.1700
Data Index: 4816200 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5836. Min Act: -0.1700
Data Index: 4187193 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5680. Min Act: -0.1700
Data Index: 4720201 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5836. Min Act: -0.1700
Data Index: 7162127 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8652. Min Range: -3.8652
Max Act: 3.5523. Min Act: -0.1700
Data Index: 5774805 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19