Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.6531. Min Act: -0.1700
Data Index: 3009315 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.5906. Min Act: -0.1700
Data Index: 7578676 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.5281. Min Act: -0.1700
Data Index: 8084167 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.5281. Min Act: -0.1700
Data Index: 3727607 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.5281. Min Act: -0.1700
Data Index: 8668892 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4656. Min Act: -0.1700
Data Index: 1662369 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4656. Min Act: -0.1700
Data Index: 1789529 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 3986273 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 7889757 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 6888866 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 8540756 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 4715226 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 2490921 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 8303790 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 6297507 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 1337276 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.4031. Min Act: -0.1700
Data Index: 6048185 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.3406. Min Act: -0.1700
Data Index: 7078473 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.3406. Min Act: -0.1700
Data Index: 5514084 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6531. Min Range: -7.6531
Max Act: 7.3406. Min Act: -0.1700
Data Index: 7659202 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19