Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.7096. Min Act: -0.1700
Data Index: 1250900 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.6783. Min Act: -0.1700
Data Index: 6572016 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5844. Min Act: -0.1700
Data Index: 1550038 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5844. Min Act: -0.1700
Data Index: 4597068 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.6157. Min Act: -0.1700
Data Index: 1550044 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 956558 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.6157. Min Act: -0.1700
Data Index: 5911607 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5844. Min Act: -0.1700
Data Index: 499600 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 5049718 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5218. Min Act: -0.1700
Data Index: 6032887 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 5984253 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 831577 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 6435410 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 48270 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5531. Min Act: -0.1700
Data Index: 5031478 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5218. Min Act: -0.1700
Data Index: 3162811 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.5218. Min Act: -0.1700
Data Index: 2955772 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.4904. Min Act: -0.1700
Data Index: 592609 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.4904. Min Act: -0.1700
Data Index: 361240 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7096. Min Range: -3.7096
Max Act: 3.4904. Min Act: -0.1700
Data Index: 1756790 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19