Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0506. Min Range: -5.0506
Max Act: 5.0506. Min Act: -0.1700
Data Index: 187320 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6349336 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9256. Min Act: -0.1700
Data Index: 3818752 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9568. Min Act: -0.1700
Data Index: 4267824 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9256. Min Act: -0.1700
Data Index: 738053 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9256. Min Act: -0.1700
Data Index: 591634 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9256. Min Act: -0.1700
Data Index: 4707600 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.9256. Min Act: -0.1700
Data Index: 8157658 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8631. Min Act: -0.1700
Data Index: 4154356 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8631. Min Act: -0.1700
Data Index: 3457609 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8631. Min Act: -0.1700
Data Index: 4860910 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8943. Min Act: -0.1700
Data Index: 6453525 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8631. Min Act: -0.1700
Data Index: 5067939 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8631. Min Act: -0.1700
Data Index: 3579390 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8631. Min Act: -0.1700
Data Index: 781655 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8318. Min Act: -0.1700
Data Index: 7367299 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8318. Min Act: -0.1700
Data Index: 3230463 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8318. Min Act: -0.1700
Data Index: 6369672 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8318. Min Act: -0.1700
Data Index: 4299567 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0506. Min Range: -5.0506
Max Act: 4.8006. Min Act: -0.1700
Data Index: 5562213 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19