Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.1735. Min Range: -17.1735
Max Act: 17.1735. Min Act: -0.1700
Data Index: 7390621 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.5485. Min Act: -0.1700
Data Index: 4079298 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.4235. Min Act: -0.1700
Data Index: 5499903 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.1735. Min Act: -0.1700
Data Index: 6237058 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.1735. Min Act: -0.1700
Data Index: 4749582 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.1735. Min Act: -0.1700
Data Index: 5198622 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.0485. Min Act: -0.1700
Data Index: 4041389 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1735. Min Range: -17.1735
Max Act: 16.0485. Min Act: -0.1700
Data Index: 3223656 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.9235. Min Act: -0.1700
Data Index: 6474710 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.9235. Min Act: -0.1700
Data Index: 824567 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.9235. Min Act: -0.1700
Data Index: 6625650 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.9235. Min Act: -0.1700
Data Index: 2502811 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.9235. Min Act: -0.1700
Data Index: 675284 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.7985. Min Act: -0.1700
Data Index: 8215156 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.7985. Min Act: -0.1700
Data Index: 3189089 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.6735. Min Act: -0.1700
Data Index: 2007892 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.7360. Min Act: -0.1700
Data Index: 4531005 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.7360. Min Act: -0.1700
Data Index: 3048228 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.7360. Min Act: -0.1700
Data Index: 2832934 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1735. Min Range: -17.1735
Max Act: 15.6735. Min Act: -0.1700
Data Index: 7138592 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19