Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4132 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.1644. Min Act: -0.1700
Data Index: 6959470 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.1332. Min Act: -0.1700
Data Index: 2944916 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.1644. Min Act: -0.1700
Data Index: 3783858 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.0707. Min Act: -0.1700
Data Index: 7181285 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.0707. Min Act: -0.1700
Data Index: 6056502 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.0082. Min Act: -0.1700
Data Index: 7911214 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1644. Min Range: -7.1644
Max Act: 7.0082. Min Act: -0.1700
Data Index: 206760 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.9769. Min Act: -0.1700
Data Index: 4330741 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.9144. Min Act: -0.1700
Data Index: 2605480 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.7894. Min Act: -0.1700
Data Index: 8134991 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8713185 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.7269. Min Act: -0.1700
Data Index: 7392460 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6957. Min Act: -0.1700
Data Index: 8793797 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6644. Min Act: -0.1700
Data Index: 615914 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6644. Min Act: -0.1700
Data Index: 4400200 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6332. Min Act: -0.1700
Data Index: 4810475 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6019. Min Act: -0.1700
Data Index: 806897 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6019. Min Act: -0.1700
Data Index: 3908206 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6332. Min Act: -0.1700
Data Index: 5656523 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1644. Min Range: -7.1644
Max Act: 6.6019. Min Act: -0.1700
Data Index: 2750852 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19