Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4904 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.4645. Min Act: -0.1700
Data Index: 2903326 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.2770. Min Act: -0.1700
Data Index: 7042855 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.2458. Min Act: -0.1700
Data Index: 5291691 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.2458. Min Act: -0.1700
Data Index: 4461367 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.1833. Min Act: -0.1700
Data Index: 5290076 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.1208. Min Act: -0.1700
Data Index: 8548593 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0895. Min Act: -0.1700
Data Index: 8725330 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0895. Min Act: -0.1700
Data Index: 7432607 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0583. Min Act: -0.1700
Data Index: 5166740 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0583. Min Act: -0.1700
Data Index: 4574028 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0583. Min Act: -0.1700
Data Index: 7593209 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0583. Min Act: -0.1700
Data Index: 6515686 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0270. Min Act: -0.1700
Data Index: 6729467 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4645. Min Range: -6.4645
Max Act: 6.0583. Min Act: -0.1700
Data Index: 2992503 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4645. Min Range: -6.4645
Max Act: 5.9958. Min Act: -0.1700
Data Index: 3393587 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4645. Min Range: -6.4645
Max Act: 5.9958. Min Act: -0.1700
Data Index: 5205666 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4645. Min Range: -6.4645
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2027382 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4645. Min Range: -6.4645
Max Act: 5.9958. Min Act: -0.1700
Data Index: 8092069 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4645. Min Range: -6.4645
Max Act: 5.9958. Min Act: -0.1700
Data Index: 296011 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4645. Min Range: -6.4645
Max Act: 5.9958. Min Act: -0.1700
Data Index: 1131580 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19