Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1962. Min Range: -6.1962
Max Act: 6.1962. Min Act: -0.1700
Data Index: 5672523 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1962. Min Range: -6.1962
Max Act: 6.0400. Min Act: -0.1700
Data Index: 438495 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1962. Min Range: -6.1962
Max Act: 6.0400. Min Act: -0.1700
Data Index: 7965478 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.9462. Min Act: -0.1700
Data Index: 7395824 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.9150. Min Act: -0.1700
Data Index: 3965221 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.9150. Min Act: -0.1700
Data Index: 7965484 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8837. Min Act: -0.1700
Data Index: 3138212 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8837. Min Act: -0.1700
Data Index: 6291963 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8837. Min Act: -0.1700
Data Index: 1596037 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8837. Min Act: -0.1700
Data Index: 24582 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8212. Min Act: -0.1700
Data Index: 2817418 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8212. Min Act: -0.1700
Data Index: 1596039 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8212. Min Act: -0.1700
Data Index: 2061961 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.8212. Min Act: -0.1700
Data Index: 8224701 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.7900. Min Act: -0.1700
Data Index: 6487123 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.7900. Min Act: -0.1700
Data Index: 7965490 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.7900. Min Act: -0.1700
Data Index: 3965207 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.7900. Min Act: -0.1700
Data Index: 6710038 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.7587. Min Act: -0.1700
Data Index: 5216175 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1962. Min Range: -6.1962
Max Act: 5.7587. Min Act: -0.1700
Data Index: 6487117 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19