Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2398 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1119. Min Range: -4.1119
Max Act: 4.1119. Min Act: -0.1700
Data Index: 313288 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1119. Min Range: -4.1119
Max Act: 4.0806. Min Act: -0.1700
Data Index: 5976897 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1119. Min Range: -4.1119
Max Act: 4.0493. Min Act: -0.1700
Data Index: 2222015 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1119. Min Range: -4.1119
Max Act: 4.0493. Min Act: -0.1700
Data Index: 5281678 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1119. Min Range: -4.1119
Max Act: 4.0181. Min Act: -0.1700
Data Index: 5056143 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9868. Min Act: -0.1700
Data Index: 2414061 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9868. Min Act: -0.1700
Data Index: 1241685 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9868. Min Act: -0.1700
Data Index: 7422134 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9556. Min Act: -0.1700
Data Index: 2906900 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9556. Min Act: -0.1700
Data Index: 1366337 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9243. Min Act: -0.1700
Data Index: 7778156 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9243. Min Act: -0.1700
Data Index: 3712292 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9243. Min Act: -0.1700
Data Index: 1013877 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9243. Min Act: -0.1700
Data Index: 1857372 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.9243. Min Act: -0.1700
Data Index: 5220518 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.8618. Min Act: -0.1700
Data Index: 7905924 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.8930. Min Act: -0.1700
Data Index: 8562618 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.8930. Min Act: -0.1700
Data Index: 2218497 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.8930. Min Act: -0.1700
Data Index: 2916899 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1119. Min Range: -4.1119
Max Act: 3.8930. Min Act: -0.1700
Data Index: 5596782 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19