Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.6794. Min Act: -0.1700
Data Index: 2923360 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.4294. Min Act: -0.1700
Data Index: 7629263 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.3357. Min Act: -0.1700
Data Index: 7386633 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.3357. Min Act: -0.1700
Data Index: 7629250 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.3044. Min Act: -0.1700
Data Index: 5087867 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 3709 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 3228 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 4054 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 3441 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 6048 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 1106 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 5038 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 1254 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 5812 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 956 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 292 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 5730 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 5868 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 3984 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6794. Min Range: -4.6794
Max Act: 4.2732. Min Act: -0.1700
Data Index: 912 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19