Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4400 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 4811017 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.9531. Min Act: -0.1700
Data Index: 8401977 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.8906. Min Act: -0.1700
Data Index: 6682159 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.8906. Min Act: -0.1700
Data Index: 8575797 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.8906. Min Act: -0.1700
Data Index: 4890206 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.8594. Min Act: -0.1700
Data Index: 6925211 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.8281. Min Act: -0.1700
Data Index: 3529145 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.8281. Min Act: -0.1700
Data Index: 3843850 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7969. Min Act: -0.1700
Data Index: 2870902 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7969. Min Act: -0.1700
Data Index: 2408608 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7969. Min Act: -0.1700
Data Index: 6157864 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7656. Min Act: -0.1700
Data Index: 1299236 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7656. Min Act: -0.1700
Data Index: 1498375 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7031. Min Act: -0.1700
Data Index: 1731133 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.7031. Min Act: -0.1700
Data Index: 1928425 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.6406. Min Act: -0.1700
Data Index: 671891 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.6406. Min Act: -0.1700
Data Index: 7680413 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.6406. Min Act: -0.1700
Data Index: 800200 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.6094. Min Act: -0.1700
Data Index: 2049862 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9844. Min Range: -5.9844
Max Act: 5.6094. Min Act: -0.1700
Data Index: 7792188 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19