Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3997. Min Range: -7.3997
Max Act: 7.3997. Min Act: -0.1700
Data Index: 8585391 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3997. Min Range: -7.3997
Max Act: 7.3997. Min Act: -0.1700
Data Index: 4101846 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3997. Min Range: -7.3997
Max Act: 7.1497. Min Act: -0.1700
Data Index: 512957 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.9622. Min Act: -0.1700
Data Index: 2941658 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.8997. Min Act: -0.1700
Data Index: 4652844 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.8997. Min Act: -0.1700
Data Index: 3748022 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.8372. Min Act: -0.1700
Data Index: 3392159 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.7747. Min Act: -0.1700
Data Index: 6331339 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.8372. Min Act: -0.1700
Data Index: 386396 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.7747. Min Act: -0.1700
Data Index: 1285845 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.7122. Min Act: -0.1700
Data Index: 8419584 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.7122. Min Act: -0.1700
Data Index: 147689 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.6810. Min Act: -0.1700
Data Index: 363316 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.6497. Min Act: -0.1700
Data Index: 3030546 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.6497. Min Act: -0.1700
Data Index: 4717891 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.6185. Min Act: -0.1700
Data Index: 5498547 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.6497. Min Act: -0.1700
Data Index: 309617 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.5872. Min Act: -0.1700
Data Index: 2094955 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.5872. Min Act: -0.1700
Data Index: 631332 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3997. Min Range: -7.3997
Max Act: 6.5872. Min Act: -0.1700
Data Index: 1656825 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19