Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.3119. Min Act: -0.1700
Data Index: 7997712 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.1232. Min Act: -0.1700
Data Index: 3048816 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.1390. Min Act: -0.1700
Data Index: 565833 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.1704. Min Act: -0.1700
Data Index: 8023249 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.1232. Min Act: -0.1700
Data Index: 5517095 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0602. Min Act: -0.1700
Data Index: 5005682 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0602. Min Act: -0.1700
Data Index: 8515336 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0602. Min Act: -0.1700
Data Index: 6293670 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0444. Min Act: -0.1700
Data Index: 581934 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0444. Min Act: -0.1700
Data Index: 2086350 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9970. Min Act: -0.1700
Data Index: 1742767 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0128. Min Act: -0.1700
Data Index: 3647346 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3119. Min Range: -3.3119
Max Act: 3.0128. Min Act: -0.1700
Data Index: 5100517 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9970. Min Act: -0.1700
Data Index: 704383 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9495. Min Act: -0.1700
Data Index: 3659531 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9495. Min Act: -0.1700
Data Index: 1642998 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9495. Min Act: -0.1700
Data Index: 428945 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9337. Min Act: -0.1700
Data Index: 2674411 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9337. Min Act: -0.1700
Data Index: 1113712 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3119. Min Range: -3.3119
Max Act: 2.9337. Min Act: -0.1700
Data Index: 1038416 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19