Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5733 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3018. Min Range: -5.3018
Max Act: 5.3018. Min Act: -0.1700
Data Index: 1136763 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3018. Min Range: -5.3018
Max Act: 5.0205. Min Act: -0.1700
Data Index: 4568447 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.9893. Min Act: -0.1700
Data Index: 7060077 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.9268. Min Act: -0.1700
Data Index: 7561807 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.9268. Min Act: -0.1700
Data Index: 4576632 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.9268. Min Act: -0.1700
Data Index: 8415503 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1511067 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.8955. Min Act: -0.1700
Data Index: 3787232 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.8018. Min Act: -0.1700
Data Index: 4314396 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.8018. Min Act: -0.1700
Data Index: 2766829 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.7705. Min Act: -0.1700
Data Index: 1410618 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.8018. Min Act: -0.1700
Data Index: 4235495 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.7393. Min Act: -0.1700
Data Index: 3984355 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.7393. Min Act: -0.1700
Data Index: 3537363 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.7080. Min Act: -0.1700
Data Index: 1503977 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.7080. Min Act: -0.1700
Data Index: 1985037 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.7393. Min Act: -0.1700
Data Index: 4616553 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.6768. Min Act: -0.1700
Data Index: 820374 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.6768. Min Act: -0.1700
Data Index: 7093213 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3018. Min Range: -5.3018
Max Act: 4.6455. Min Act: -0.1700
Data Index: 5698555 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19