Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1520. Min Range: -6.1520
Max Act: 6.1520. Min Act: -0.1700
Data Index: 905091 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1520. Min Range: -6.1520
Max Act: 6.1207. Min Act: -0.1700
Data Index: 4139834 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1520. Min Range: -6.1520
Max Act: 6.0582. Min Act: -0.1700
Data Index: 7864366 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.9957. Min Act: -0.1700
Data Index: 7078530 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.9957. Min Act: -0.1700
Data Index: 2591998 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.9645. Min Act: -0.1700
Data Index: 8544614 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.9020. Min Act: -0.1700
Data Index: 2348911 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.9020. Min Act: -0.1700
Data Index: 5778851 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.9020. Min Act: -0.1700
Data Index: 4895047 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8395. Min Act: -0.1700
Data Index: 3278504 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8707. Min Act: -0.1700
Data Index: 1707313 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8395. Min Act: -0.1700
Data Index: 732474 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8082. Min Act: -0.1700
Data Index: 119984 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8082. Min Act: -0.1700
Data Index: 8678423 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8082. Min Act: -0.1700
Data Index: 330803 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.7770. Min Act: -0.1700
Data Index: 1344062 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.7770. Min Act: -0.1700
Data Index: 4240183 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.8082. Min Act: -0.1700
Data Index: 4347546 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.7457. Min Act: -0.1700
Data Index: 3870595 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1520. Min Range: -6.1520
Max Act: 5.7457. Min Act: -0.1700
Data Index: 954563 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19