Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2195. Min Range: -6.2195
Max Act: 6.2195. Min Act: -0.1700
Data Index: 5267673 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2195. Min Range: -6.2195
Max Act: 6.0632. Min Act: -0.1700
Data Index: 8592914 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2195. Min Range: -6.2195
Max Act: 6.0632. Min Act: -0.1700
Data Index: 5679367 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.8445. Min Act: -0.1700
Data Index: 7180746 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.8445. Min Act: -0.1700
Data Index: 8566979 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.8445. Min Act: -0.1700
Data Index: 5087379 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.8132. Min Act: -0.1700
Data Index: 739455 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.7507. Min Act: -0.1700
Data Index: 3877030 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.7507. Min Act: -0.1700
Data Index: 4977414 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.7195. Min Act: -0.1700
Data Index: 4424089 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.7195. Min Act: -0.1700
Data Index: 8652800 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.6570. Min Act: -0.1700
Data Index: 4571099 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.6570. Min Act: -0.1700
Data Index: 2025687 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.6257. Min Act: -0.1700
Data Index: 2674011 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.6257. Min Act: -0.1700
Data Index: 2363354 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.5632. Min Act: -0.1700
Data Index: 6235118 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.5632. Min Act: -0.1700
Data Index: 1579856 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.5320. Min Act: -0.1700
Data Index: 2744175 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.5320. Min Act: -0.1700
Data Index: 5029888 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2195. Min Range: -6.2195
Max Act: 5.5320. Min Act: -0.1700
Data Index: 6786846 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19