Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.7860. Min Act: -0.1700
Data Index: 5595042 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.6921. Min Act: -0.1700
Data Index: 185375 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.6765. Min Act: -0.1700
Data Index: 3020400 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.6139. Min Act: -0.1700
Data Index: 5274451 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.5982. Min Act: -0.1700
Data Index: 1745329 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.5669. Min Act: -0.1700
Data Index: 177597 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4730. Min Act: -0.1700
Data Index: 4011884 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4886. Min Act: -0.1700
Data Index: 3600132 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4886. Min Act: -0.1700
Data Index: 88301 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4573. Min Act: -0.1700
Data Index: 7256168 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4573. Min Act: -0.1700
Data Index: 7933300 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4260. Min Act: -0.1700
Data Index: 5964600 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4573. Min Act: -0.1700
Data Index: 3589606 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4103. Min Act: -0.1700
Data Index: 3237503 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.3946. Min Act: -0.1700
Data Index: 7995125 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4103. Min Act: -0.1700
Data Index: 4210904 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.4103. Min Act: -0.1700
Data Index: 2016152 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.3946. Min Act: -0.1700
Data Index: 3232921 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.3946. Min Act: -0.1700
Data Index: 5888483 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7860. Min Range: -3.7860
Max Act: 3.3946. Min Act: -0.1700
Data Index: 3772334 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19