Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.4474. Min Act: -0.1700
Data Index: 6642655 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.4474. Min Act: -0.1700
Data Index: 145103 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.4162. Min Act: -0.1700
Data Index: 3953765 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3849. Min Act: -0.1700
Data Index: 6437230 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.4162. Min Act: -0.1700
Data Index: 7424533 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3849. Min Act: -0.1700
Data Index: 5273098 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3849. Min Act: -0.1700
Data Index: 913799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3537. Min Act: -0.1700
Data Index: 4030103 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3537. Min Act: -0.1700
Data Index: 8688177 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3537. Min Act: -0.1700
Data Index: 7781506 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3537. Min Act: -0.1700
Data Index: 7790381 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3537. Min Act: -0.1700
Data Index: 3826278 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3224. Min Act: -0.1700
Data Index: 2936964 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.2912. Min Act: -0.1700
Data Index: 8646280 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3224. Min Act: -0.1700
Data Index: 8104632 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3224. Min Act: -0.1700
Data Index: 3658548 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3224. Min Act: -0.1700
Data Index: 6112010 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.3224. Min Act: -0.1700
Data Index: 5930847 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.2599. Min Act: -0.1700
Data Index: 175518 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4474. Min Range: -4.4474
Max Act: 4.2912. Min Act: -0.1700
Data Index: 4030457 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19