Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0974. Min Range: -3.0974
Max Act: 3.0974. Min Act: -0.1700
Data Index: 5387283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0974. Min Range: -3.0974
Max Act: 3.0501. Min Act: -0.1700
Data Index: 6307329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0974. Min Range: -3.0974
Max Act: 3.0501. Min Act: -0.1700
Data Index: 3827856 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0974. Min Range: -3.0974
Max Act: 3.0028. Min Act: -0.1700
Data Index: 4438050 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0974. Min Range: -3.0974
Max Act: 3.0028. Min Act: -0.1700
Data Index: 8817191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9869. Min Act: -0.1700
Data Index: 6209443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9869. Min Act: -0.1700
Data Index: 4605966 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9869. Min Act: -0.1700
Data Index: 6349074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 295861 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9553. Min Act: -0.1700
Data Index: 4438054 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 2740312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 7270401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 7136475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 6206970 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 6590238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 3810981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9711. Min Act: -0.1700
Data Index: 4706758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9553. Min Act: -0.1700
Data Index: 298663 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9395. Min Act: -0.1700
Data Index: 230492 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0974. Min Range: -3.0974
Max Act: 2.9553. Min Act: -0.1700
Data Index: 3060799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19