Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2155 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.6726. Min Act: -0.1700
Data Index: 1055566 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.6100. Min Act: -0.1700
Data Index: 489878 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.5631. Min Act: -0.1700
Data Index: 1849919 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.5631. Min Act: -0.1700
Data Index: 3147816 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.5161. Min Act: -0.1700
Data Index: 3852286 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.5318. Min Act: -0.1700
Data Index: 3035105 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.5161. Min Act: -0.1700
Data Index: 6603906 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.4848. Min Act: -0.1700
Data Index: 876539 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.4848. Min Act: -0.1700
Data Index: 1993967 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.4378. Min Act: -0.1700
Data Index: 6121627 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.4064. Min Act: -0.1700
Data Index: 1364874 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.4221. Min Act: -0.1700
Data Index: 4097135 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3907. Min Act: -0.1700
Data Index: 6277006 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3751. Min Act: -0.1700
Data Index: 6967173 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3751. Min Act: -0.1700
Data Index: 4974021 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3594. Min Act: -0.1700
Data Index: 3532448 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3437. Min Act: -0.1700
Data Index: 213013 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3437. Min Act: -0.1700
Data Index: 1858263 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3280. Min Act: -0.1700
Data Index: 8354705 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6726. Min Range: -3.6726
Max Act: 3.3437. Min Act: -0.1700
Data Index: 5672583 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19