Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 154 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.5176. Min Act: -0.1700
Data Index: 4275203 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4863. Min Act: -0.1700
Data Index: 251273 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 5525705 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 4275199 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2875107 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2568759 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7441559 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 5535978 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3926. Min Act: -0.1700
Data Index: 6521759 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3926. Min Act: -0.1700
Data Index: 4410681 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3926. Min Act: -0.1700
Data Index: 4868071 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3613. Min Act: -0.1700
Data Index: 4880878 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3613. Min Act: -0.1700
Data Index: 3433353 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3613. Min Act: -0.1700
Data Index: 4410684 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3301. Min Act: -0.1700
Data Index: 3178269 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3613. Min Act: -0.1700
Data Index: 4410682 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3301. Min Act: -0.1700
Data Index: 2374389 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3301. Min Act: -0.1700
Data Index: 2890251 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3301. Min Act: -0.1700
Data Index: 6283574 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5176. Min Range: -5.5176
Max Act: 5.3301. Min Act: -0.1700
Data Index: 4410683 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19