Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4672. Min Range: -6.4672
Max Act: 6.4672. Min Act: -0.1700
Data Index: 6635335 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.9672. Min Act: -0.1700
Data Index: 3224066 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.9672. Min Act: -0.1700
Data Index: 6759072 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.9047. Min Act: -0.1700
Data Index: 7314764 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.9047. Min Act: -0.1700
Data Index: 5678899 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.8734. Min Act: -0.1700
Data Index: 5653547 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.8734. Min Act: -0.1700
Data Index: 24740 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7797. Min Act: -0.1700
Data Index: 8546154 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7797. Min Act: -0.1700
Data Index: 1603632 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7797. Min Act: -0.1700
Data Index: 7358255 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7797. Min Act: -0.1700
Data Index: 3424825 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7797. Min Act: -0.1700
Data Index: 7233678 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7484. Min Act: -0.1700
Data Index: 3372393 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7172. Min Act: -0.1700
Data Index: 5367288 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.6859. Min Act: -0.1700
Data Index: 2128837 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7172. Min Act: -0.1700
Data Index: 2793869 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7172. Min Act: -0.1700
Data Index: 5977948 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.7172. Min Act: -0.1700
Data Index: 1596213 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.6859. Min Act: -0.1700
Data Index: 3342066 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4672. Min Range: -6.4672
Max Act: 5.6547. Min Act: -0.1700
Data Index: 5550884 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19