Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0722. Min Range: -5.0722
Max Act: 5.0722. Min Act: -0.1700
Data Index: 5895009 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.8535. Min Act: -0.1700
Data Index: 4930156 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.7910. Min Act: -0.1700
Data Index: 2246542 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.7597. Min Act: -0.1700
Data Index: 7448490 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.7285. Min Act: -0.1700
Data Index: 6848515 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6972. Min Act: -0.1700
Data Index: 3660214 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1848589 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6660. Min Act: -0.1700
Data Index: 1584098 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6660. Min Act: -0.1700
Data Index: 2429691 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6660. Min Act: -0.1700
Data Index: 7004305 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6660. Min Act: -0.1700
Data Index: 564998 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6347. Min Act: -0.1700
Data Index: 4494087 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6347. Min Act: -0.1700
Data Index: 2397592 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6347. Min Act: -0.1700
Data Index: 5593109 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6347. Min Act: -0.1700
Data Index: 1987514 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6035. Min Act: -0.1700
Data Index: 168305 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6035. Min Act: -0.1700
Data Index: 2905354 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.6035. Min Act: -0.1700
Data Index: 6026551 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.5722. Min Act: -0.1700
Data Index: 2122639 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0722. Min Range: -5.0722
Max Act: 4.5722. Min Act: -0.1700
Data Index: 4460641 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19