Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.4499. Min Act: -0.1700
Data Index: 4895297 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.2312. Min Act: -0.1700
Data Index: 1256629 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.1062. Min Act: -0.1700
Data Index: 6346321 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.1374. Min Act: -0.1700
Data Index: 54267 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4499. Min Range: -8.4499
Max Act: 8.0437. Min Act: -0.1700
Data Index: 2736216 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.9499. Min Act: -0.1700
Data Index: 3937210 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.9499. Min Act: -0.1700
Data Index: 6687777 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.8874. Min Act: -0.1700
Data Index: 3532029 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.8562. Min Act: -0.1700
Data Index: 5716785 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.8562. Min Act: -0.1700
Data Index: 4336995 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.8249. Min Act: -0.1700
Data Index: 3248102 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7937. Min Act: -0.1700
Data Index: 177994 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7937. Min Act: -0.1700
Data Index: 4201799 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7624. Min Act: -0.1700
Data Index: 4608519 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.7624. Min Act: -0.1700
Data Index: 4909003 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 1810279 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 8306634 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 1646906 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6999. Min Act: -0.1700
Data Index: 7472613 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4499. Min Range: -8.4499
Max Act: 7.6687. Min Act: -0.1700
Data Index: 4930677 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19