Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.5201. Min Act: -0.1700
Data Index: 6055230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.5201. Min Act: -0.1700
Data Index: 7716447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.5201. Min Act: -0.1700
Data Index: 1640570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4889. Min Act: -0.1700
Data Index: 6368065 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4889. Min Act: -0.1700
Data Index: 5254896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4889. Min Act: -0.1700
Data Index: 7303987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4576. Min Act: -0.1700
Data Index: 2443499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4576. Min Act: -0.1700
Data Index: 2454473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4576. Min Act: -0.1700
Data Index: 7559691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 3051173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 5475044 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 616360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 4380565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 6932700 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 3830906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.4264. Min Act: -0.1700
Data Index: 3721195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.3951. Min Act: -0.1700
Data Index: 4429089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.3951. Min Act: -0.1700
Data Index: 4469766 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.3951. Min Act: -0.1700
Data Index: 2799436 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5201. Min Range: -4.5201
Max Act: 4.3951. Min Act: -0.1700
Data Index: 4599460 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19