Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5855. Min Act: -0.1700
Data Index: 3393446 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5855. Min Act: -0.1700
Data Index: 6752520 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5543. Min Act: -0.1700
Data Index: 5927412 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5543. Min Act: -0.1700
Data Index: 7812883 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5543. Min Act: -0.1700
Data Index: 8327972 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5230. Min Act: -0.1700
Data Index: 6767196 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5230. Min Act: -0.1700
Data Index: 6752517 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5230. Min Act: -0.1700
Data Index: 4236529 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5230. Min Act: -0.1699
Data Index: 1030223 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.5230. Min Act: -0.1699
Data Index: 2099095 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 6752518 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 3393454 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 7123370 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 7529224 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 1623282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 818293 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1696
Data Index: 5235720 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 1623276 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 1160443 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5855. Min Range: -5.5855
Max Act: 5.4918. Min Act: -0.1700
Data Index: 525490 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19