Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4722 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.4931. Min Act: -0.1700
Data Index: 1027241 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.4618. Min Act: -0.1700
Data Index: 741194 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.3681. Min Act: -0.1700
Data Index: 1282333 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8260595 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2118. Min Act: -0.1700
Data Index: 7424087 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2431. Min Act: -0.1700
Data Index: 1282334 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2431. Min Act: -0.1700
Data Index: 741191 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2743. Min Act: -0.1700
Data Index: 1806481 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2118. Min Act: -0.1700
Data Index: 2685010 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2118. Min Act: -0.1700
Data Index: 452522 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2118. Min Act: -0.1700
Data Index: 5183938 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.2118. Min Act: -0.1700
Data Index: 741195 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1493. Min Act: -0.1700
Data Index: 1806487 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1493. Min Act: -0.1700
Data Index: 7092280 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1493. Min Act: -0.1700
Data Index: 949365 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1493. Min Act: -0.1700
Data Index: 6145568 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1181. Min Act: -0.1700
Data Index: 3758484 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1181. Min Act: -0.1700
Data Index: 7254528 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1181. Min Act: -0.1700
Data Index: 4191370 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4931. Min Range: -5.4931
Max Act: 5.1181. Min Act: -0.1700
Data Index: 4439667 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19