Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0953. Min Range: -5.0953
Max Act: 5.0953. Min Act: -0.1700
Data Index: 2599919 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.9078. Min Act: -0.1700
Data Index: 4379452 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.8453. Min Act: -0.1700
Data Index: 1148550 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.8140. Min Act: -0.1700
Data Index: 3973434 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.7828. Min Act: -0.1700
Data Index: 3806471 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.7515. Min Act: -0.1700
Data Index: 8345396 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.7515. Min Act: -0.1700
Data Index: 5954661 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.7515. Min Act: -0.1700
Data Index: 212150 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.7203. Min Act: -0.1700
Data Index: 2014927 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.7203. Min Act: -0.1700
Data Index: 7334544 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6890. Min Act: -0.1700
Data Index: 6447021 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6578. Min Act: -0.1700
Data Index: 2142076 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6890. Min Act: -0.1700
Data Index: 2765379 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6890. Min Act: -0.1700
Data Index: 6688480 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6890. Min Act: -0.1700
Data Index: 754241 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6890. Min Act: -0.1700
Data Index: 4487478 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6578. Min Act: -0.1700
Data Index: 206242 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6578. Min Act: -0.1700
Data Index: 4322716 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6578. Min Act: -0.1700
Data Index: 7389037 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0953. Min Range: -5.0953
Max Act: 4.6578. Min Act: -0.1700
Data Index: 4796400 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19