Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.7882. Min Act: -0.1700
Data Index: 630317 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.7257. Min Act: -0.1700
Data Index: 630306 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.7257. Min Act: -0.1700
Data Index: 630310 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.7257. Min Act: -0.1700
Data Index: 3312774 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.6944. Min Act: -0.1700
Data Index: 630320 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.6632. Min Act: -0.1700
Data Index: 1137541 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.6632. Min Act: -0.1700
Data Index: 630315 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.6319. Min Act: -0.1700
Data Index: 630309 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.5694. Min Act: -0.1700
Data Index: 630311 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.5382. Min Act: -0.1700
Data Index: 4553542 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.5382. Min Act: -0.1700
Data Index: 7872371 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.5069. Min Act: -0.1700
Data Index: 5607482 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.5069. Min Act: -0.1700
Data Index: 630314 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.4757. Min Act: -0.1700
Data Index: 630321 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.4444. Min Act: -0.1700
Data Index: 4330329 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.4444. Min Act: -0.1700
Data Index: 1108453 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.4132. Min Act: -0.1700
Data Index: 6857401 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.4132. Min Act: -0.1700
Data Index: 7467839 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.4132. Min Act: -0.1700
Data Index: 4525379 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7882. Min Range: -5.7882
Max Act: 5.3819. Min Act: -0.1700
Data Index: 1840827 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19