Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.5643. Min Act: -0.1700
Data Index: 6157265 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.5173. Min Act: -0.1700
Data Index: 3597954 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.4233. Min Act: -0.1700
Data Index: 573502 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.4233. Min Act: -0.1700
Data Index: 8509971 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.4076. Min Act: -0.1700
Data Index: 3582123 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3919. Min Act: -0.1700
Data Index: 5263228 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3919. Min Act: -0.1700
Data Index: 4471282 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3919. Min Act: -0.1700
Data Index: 6170352 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3606. Min Act: -0.1700
Data Index: 3628152 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3606. Min Act: -0.1700
Data Index: 5834704 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3606. Min Act: -0.1700
Data Index: 6295799 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3449. Min Act: -0.1700
Data Index: 7603363 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3449. Min Act: -0.1700
Data Index: 6106321 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3449. Min Act: -0.1700
Data Index: 5239047 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3292. Min Act: -0.1700
Data Index: 3402612 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3292. Min Act: -0.1700
Data Index: 6502393 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.2978. Min Act: -0.1700
Data Index: 6869681 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3135. Min Act: -0.1700
Data Index: 732915 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3135. Min Act: -0.1700
Data Index: 2417984 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5643. Min Range: -3.5643
Max Act: 3.3135. Min Act: -0.1700
Data Index: 3139015 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19