Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2238 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.3949. Min Act: -0.1700
Data Index: 6621686 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.3949. Min Act: -0.1700
Data Index: 6926473 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.3636. Min Act: -0.1700
Data Index: 6926474 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.3324. Min Act: -0.1700
Data Index: 3480830 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.2699. Min Act: -0.1700
Data Index: 158287 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.2699. Min Act: -0.1700
Data Index: 5476294 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.2699. Min Act: -0.1700
Data Index: 3596455 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.2074. Min Act: -0.1700
Data Index: 340656 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.2074. Min Act: -0.1700
Data Index: 5476295 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.1761. Min Act: -0.1700
Data Index: 158286 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.1449. Min Act: -0.1700
Data Index: 5476296 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.1449. Min Act: -0.1700
Data Index: 3596453 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.0199. Min Act: -0.1700
Data Index: 3480829 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3949. Min Range: -5.3949
Max Act: 5.0199. Min Act: -0.1700
Data Index: 2473774 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3949. Min Range: -5.3949
Max Act: 4.9261. Min Act: -0.1700
Data Index: 5716867 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3949. Min Range: -5.3949
Max Act: 4.8324. Min Act: -0.1700
Data Index: 4255114 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3949. Min Range: -5.3949
Max Act: 4.7699. Min Act: -0.1700
Data Index: 8062096 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3949. Min Range: -5.3949
Max Act: 4.7386. Min Act: -0.1700
Data Index: 3102261 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3949. Min Range: -5.3949
Max Act: 4.6761. Min Act: -0.1700
Data Index: 7755120 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3949. Min Range: -5.3949
Max Act: 4.6449. Min Act: -0.1700
Data Index: 3337137 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19