Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.6722. Min Act: -0.1700
Data Index: 183290 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.6722. Min Act: -0.1700
Data Index: 1021032 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.5785. Min Act: -0.1700
Data Index: 4572491 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.4847. Min Act: -0.1700
Data Index: 7525171 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.4222. Min Act: -0.1700
Data Index: 5442541 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.3910. Min Act: -0.1700
Data Index: 6622805 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.4222. Min Act: -0.1700
Data Index: 2074326 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.3910. Min Act: -0.1700
Data Index: 2723072 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.3597. Min Act: -0.1700
Data Index: 5999378 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7163402 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.3285. Min Act: -0.1700
Data Index: 1057558 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2972. Min Act: -0.1700
Data Index: 6554240 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2972. Min Act: -0.1700
Data Index: 6866828 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2972. Min Act: -0.1700
Data Index: 914881 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2660. Min Act: -0.1700
Data Index: 492114 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2660. Min Act: -0.1700
Data Index: 7476840 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2660. Min Act: -0.1700
Data Index: 2320814 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2035. Min Act: -0.1700
Data Index: 713988 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2035. Min Act: -0.1700
Data Index: 5399921 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6722. Min Range: -5.6722
Max Act: 5.2035. Min Act: -0.1700
Data Index: 201412 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19