Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 7893917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 6659894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 4733739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 724661 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 4289485 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 3896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 2570334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 2338675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 8726804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 8541240 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 8094206 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 1706135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 4929561 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 6510251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 2797555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 3361019 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 3781831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 3813955 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 4579803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8044. Min Act: -0.1700
Data Index: 4894365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19