Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0986. Min Range: -7.0986
Max Act: 7.0986. Min Act: -0.1700
Data Index: 7663698 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.9423. Min Act: -0.1700
Data Index: 7539215 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.8798. Min Act: -0.1700
Data Index: 896406 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.8486. Min Act: -0.1700
Data Index: 1375181 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.8486. Min Act: -0.1700
Data Index: 3651036 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 669248 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7548. Min Act: -0.1700
Data Index: 3556176 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7548. Min Act: -0.1700
Data Index: 2575603 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 397991 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 2935038 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 8118249 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 4660632 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 4976367 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.6923. Min Act: -0.1700
Data Index: 2575605 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.6923. Min Act: -0.1700
Data Index: 3687025 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.7236. Min Act: -0.1700
Data Index: 1582841 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.6298. Min Act: -0.1700
Data Index: 252576 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.5986. Min Act: -0.1700
Data Index: 3081091 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.5673. Min Act: -0.1700
Data Index: 5372185 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0986. Min Range: -7.0986
Max Act: 6.5986. Min Act: -0.1700
Data Index: 1016485 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19