Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0134. Min Range: -2.0134
Max Act: 2.0134. Min Act: -0.1700
Data Index: 3078725 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9796. Min Act: -0.1700
Data Index: 2932674 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9626. Min Act: -0.1700
Data Index: 6576388 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9626. Min Act: -0.1700
Data Index: 5003262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9457. Min Act: -0.1700
Data Index: 8610628 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9117. Min Act: -0.1700
Data Index: 2418381 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9117. Min Act: -0.1700
Data Index: 2369684 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9117. Min Act: -0.1700
Data Index: 3745931 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.9117. Min Act: -0.1699
Data Index: 980908 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8946. Min Act: -0.1700
Data Index: 2248871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 1877569 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 3773973 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8946. Min Act: -0.1700
Data Index: 7784635 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 3532256 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 1699747 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8946. Min Act: -0.1700
Data Index: 3092818 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 552351 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 7491300 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8775. Min Act: -0.1700
Data Index: 512724 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0134. Min Range: -2.0134
Max Act: 1.8604. Min Act: -0.1700
Data Index: 6464576 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19