Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.3435. Min Act: -0.1700
Data Index: 8210282 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.2185. Min Act: -0.1700
Data Index: 5798116 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.1873. Min Act: -0.1700
Data Index: 7340660 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.1560. Min Act: -0.1700
Data Index: 7528891 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.1560. Min Act: -0.1700
Data Index: 8009020 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.0935. Min Act: -0.1700
Data Index: 5495590 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.0623. Min Act: -0.1700
Data Index: 5218112 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.0623. Min Act: -0.1700
Data Index: 3256314 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3435. Min Range: -6.3435
Max Act: 6.0310. Min Act: -0.1700
Data Index: 1434034 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9998. Min Act: -0.1700
Data Index: 2726519 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9685. Min Act: -0.1700
Data Index: 1160817 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9685. Min Act: -0.1700
Data Index: 6066411 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9373. Min Act: -0.1700
Data Index: 4668429 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9685. Min Act: -0.1700
Data Index: 5525153 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9373. Min Act: -0.1700
Data Index: 8555126 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.9060. Min Act: -0.1700
Data Index: 6442716 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.8748. Min Act: -0.1700
Data Index: 8620124 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.8435. Min Act: -0.1700
Data Index: 7364409 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.8435. Min Act: -0.1700
Data Index: 8075554 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3435. Min Range: -6.3435
Max Act: 5.8435. Min Act: -0.1700
Data Index: 6393423 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19