Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5756 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.4711. Min Act: -0.1700
Data Index: 8575753 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.3771. Min Act: -0.1700
Data Index: 7354238 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.3614. Min Act: -0.1700
Data Index: 8466615 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.3143. Min Act: -0.1700
Data Index: 8188133 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.2358. Min Act: -0.1700
Data Index: 3541642 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.2358. Min Act: -0.1700
Data Index: 2655002 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.2044. Min Act: -0.1700
Data Index: 6528810 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.2044. Min Act: -0.1700
Data Index: 4092169 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.2044. Min Act: -0.1700
Data Index: 6766233 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.2044. Min Act: -0.1700
Data Index: 1261253 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1572. Min Act: -0.1700
Data Index: 698656 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1729. Min Act: -0.1700
Data Index: 2850605 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1729. Min Act: -0.1700
Data Index: 581791 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1729. Min Act: -0.1700
Data Index: 7636427 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1729. Min Act: -0.1700
Data Index: 5191181 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1572. Min Act: -0.1700
Data Index: 5803877 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1572. Min Act: -0.1700
Data Index: 6142988 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1572. Min Act: -0.1700
Data Index: 1317465 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1414. Min Act: -0.1700
Data Index: 402539 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4711. Min Range: -3.4711
Max Act: 3.1572. Min Act: -0.1700
Data Index: 8473104 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19