Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.8623. Min Act: -0.1700
Data Index: 6061181 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.7373. Min Act: -0.1700
Data Index: 3420952 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.7060. Min Act: -0.1700
Data Index: 252954 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.6123. Min Act: -0.1700
Data Index: 1685711 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.5498. Min Act: -0.1700
Data Index: 3512083 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.5185. Min Act: -0.1700
Data Index: 2589209 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.5185. Min Act: -0.1700
Data Index: 3809531 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.5185. Min Act: -0.1700
Data Index: 172817 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.4560. Min Act: -0.1700
Data Index: 6083440 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.4560. Min Act: -0.1700
Data Index: 1994443 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.4248. Min Act: -0.1700
Data Index: 287576 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.4248. Min Act: -0.1700
Data Index: 2357539 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.3935. Min Act: -0.1700
Data Index: 3895888 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.3935. Min Act: -0.1700
Data Index: 1840174 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.3623. Min Act: -0.1700
Data Index: 8076156 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.3310. Min Act: -0.1700
Data Index: 8120575 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.3310. Min Act: -0.1700
Data Index: 1473044 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.2998. Min Act: -0.1700
Data Index: 7508220 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.2998. Min Act: -0.1700
Data Index: 663200 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8623. Min Range: -5.8623
Max Act: 5.2998. Min Act: -0.1700
Data Index: 5495056 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19