Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4396. Min Act: -0.1700
Data Index: 1157247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4233. Min Act: -0.1700
Data Index: 5376828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4233. Min Act: -0.1700
Data Index: 6031264 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 7378854 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.3906. Min Act: -0.1700
Data Index: 731710 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 3583321 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 5609796 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 6775740 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 4669183 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 4430522 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 5595590 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 1331388 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 5401064 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 4264529 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 6562162 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 5235273 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 210134 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 1565536 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 453383 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4396. Min Range: -2.4396
Max Act: 2.4070. Min Act: -0.1700
Data Index: 3789464 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19