Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5805 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0658. Min Range: -4.0658
Max Act: 4.0658. Min Act: -0.1700
Data Index: 3555470 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.8157. Min Act: -0.1700
Data Index: 1128098 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.7375. Min Act: -0.1700
Data Index: 4790126 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.6593. Min Act: -0.1700
Data Index: 7826765 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.6280. Min Act: -0.1700
Data Index: 5731744 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.6280. Min Act: -0.1700
Data Index: 642489 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5967. Min Act: -0.1700
Data Index: 52735 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.6123. Min Act: -0.1700
Data Index: 1706220 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.6123. Min Act: -0.1700
Data Index: 7981148 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5810. Min Act: -0.1700
Data Index: 7489544 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5810. Min Act: -0.1700
Data Index: 3630012 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5810. Min Act: -0.1700
Data Index: 5189286 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 874650 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 3349689 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 2480095 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 3732164 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 1932554 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 2246303 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5497. Min Act: -0.1700
Data Index: 5441763 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0658. Min Range: -4.0658
Max Act: 3.5654. Min Act: -0.1700
Data Index: 2987873 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19