Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2136 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0957. Min Range: -6.0957
Max Act: 6.0957. Min Act: -0.1700
Data Index: 5571089 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.8144. Min Act: -0.1700
Data Index: 1174971 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.7832. Min Act: -0.1700
Data Index: 489884 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.7519. Min Act: -0.1700
Data Index: 1347012 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.6582. Min Act: -0.1700
Data Index: 4495370 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5957. Min Act: -0.1700
Data Index: 4003074 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5644. Min Act: -0.1700
Data Index: 1071213 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5332. Min Act: -0.1700
Data Index: 1513508 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5019. Min Act: -0.1700
Data Index: 6566381 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5332. Min Act: -0.1700
Data Index: 4137898 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5332. Min Act: -0.1700
Data Index: 2032194 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5019. Min Act: -0.1700
Data Index: 2380036 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5019. Min Act: -0.1700
Data Index: 232583 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5019. Min Act: -0.1700
Data Index: 269122 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5019. Min Act: -0.1700
Data Index: 6278555 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.5019. Min Act: -0.1700
Data Index: 3441243 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.4707. Min Act: -0.1700
Data Index: 5769378 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.4707. Min Act: -0.1700
Data Index: 3949898 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.4707. Min Act: -0.1700
Data Index: 8397542 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0957. Min Range: -6.0957
Max Act: 5.4707. Min Act: -0.1700
Data Index: 5811753 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19