Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4397 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.2692. Min Act: -0.1700
Data Index: 4456622 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.1130. Min Act: -0.1700
Data Index: 3019997 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.0817. Min Act: -0.1700
Data Index: 4703912 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2692. Min Range: -6.2692
Max Act: 6.0192. Min Act: -0.1700
Data Index: 4269086 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.9567. Min Act: -0.1700
Data Index: 4703898 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8942. Min Act: -0.1700
Data Index: 6076116 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8630. Min Act: -0.1700
Data Index: 5786089 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8317. Min Act: -0.1700
Data Index: 7361192 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8630. Min Act: -0.1700
Data Index: 3079565 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8317. Min Act: -0.1700
Data Index: 3182253 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7692. Min Act: -0.1700
Data Index: 8300503 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8005. Min Act: -0.1700
Data Index: 2555247 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.8005. Min Act: -0.1700
Data Index: 5312019 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7692. Min Act: -0.1700
Data Index: 2733287 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7380. Min Act: -0.1700
Data Index: 2077673 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7380. Min Act: -0.1700
Data Index: 4260393 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3677494 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7380. Min Act: -0.1700
Data Index: 2578423 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7380. Min Act: -0.1700
Data Index: 2417547 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2692. Min Range: -6.2692
Max Act: 5.7067. Min Act: -0.1700
Data Index: 5322147 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19