Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0524. Min Range: -4.0524
Max Act: 4.0524. Min Act: -0.1700
Data Index: 4265779 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.9586. Min Act: -0.1700
Data Index: 8132152 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.8649. Min Act: -0.1700
Data Index: 4722860 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.8023. Min Act: -0.1700
Data Index: 1027381 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.7710. Min Act: -0.1700
Data Index: 3414330 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.7398. Min Act: -0.1700
Data Index: 1913144 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.7398. Min Act: -0.1700
Data Index: 3414331 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.7085. Min Act: -0.1700
Data Index: 3187601 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.7085. Min Act: -0.1700
Data Index: 172816 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6615. Min Act: -0.1700
Data Index: 5091292 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6928. Min Act: -0.1700
Data Index: 8360911 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6615. Min Act: -0.1700
Data Index: 7947348 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6615. Min Act: -0.1700
Data Index: 6870274 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6459. Min Act: -0.1700
Data Index: 3513681 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6459. Min Act: -0.1700
Data Index: 5773489 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6459. Min Act: -0.1700
Data Index: 4853412 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6146. Min Act: -0.1700
Data Index: 5640694 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6146. Min Act: -0.1700
Data Index: 3877868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6146. Min Act: -0.1700
Data Index: 5644790 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0524. Min Range: -4.0524
Max Act: 3.6146. Min Act: -0.1700
Data Index: 3958259 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19