Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 469 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.4256. Min Act: -0.1700
Data Index: 4776625 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.3943. Min Act: -0.1700
Data Index: 3990695 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.2381. Min Act: -0.1700
Data Index: 8261162 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1443. Min Act: -0.1700
Data Index: 4122219 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1443. Min Act: -0.1700
Data Index: 4314776 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1756. Min Act: -0.1700
Data Index: 248612 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1443. Min Act: -0.1700
Data Index: 4287322 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1131. Min Act: -0.1700
Data Index: 130866 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1131. Min Act: -0.1700
Data Index: 712929 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1131. Min Act: -0.1700
Data Index: 3436132 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.1131. Min Act: -0.1700
Data Index: 8630471 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0818. Min Act: -0.1700
Data Index: 5992691 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0818. Min Act: -0.1700
Data Index: 6633861 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0506. Min Act: -0.1700
Data Index: 6622345 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0506. Min Act: -0.1700
Data Index: 5608182 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0193. Min Act: -0.1700
Data Index: 3070183 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4256. Min Range: -5.4256
Max Act: 4.9881. Min Act: -0.1700
Data Index: 2240419 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0193. Min Act: -0.1700
Data Index: 7140390 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0193. Min Act: -0.1700
Data Index: 6468112 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4256. Min Range: -5.4256
Max Act: 5.0193. Min Act: -0.1700
Data Index: 1135019 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19