Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0747. Min Range: -7.0747
Max Act: 7.0747. Min Act: -0.1700
Data Index: 3820599 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0747. Min Range: -7.0747
Max Act: 7.0434. Min Act: -0.1700
Data Index: 7940759 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0747. Min Range: -7.0747
Max Act: 7.0122. Min Act: -0.1700
Data Index: 5846484 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.9497. Min Act: -0.1700
Data Index: 6946954 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.9184. Min Act: -0.1700
Data Index: 3655480 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.9184. Min Act: -0.1700
Data Index: 3403439 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.9184. Min Act: -0.1700
Data Index: 8516817 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.9184. Min Act: -0.1700
Data Index: 7981421 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8872. Min Act: -0.1700
Data Index: 5053205 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8559. Min Act: -0.1700
Data Index: 1850057 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8872. Min Act: -0.1700
Data Index: 6773161 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8247. Min Act: -0.1700
Data Index: 3049074 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8559. Min Act: -0.1700
Data Index: 4017140 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8559. Min Act: -0.1700
Data Index: 2361433 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8559. Min Act: -0.1700
Data Index: 319181 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8559. Min Act: -0.1700
Data Index: 4422087 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8559. Min Act: -0.1700
Data Index: 260918 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8872. Min Act: -0.1700
Data Index: 3871221 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.8247. Min Act: -0.1700
Data Index: 4602370 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0747. Min Range: -7.0747
Max Act: 6.7934. Min Act: -0.1700
Data Index: 4954672 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19