Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.1612. Min Act: -0.1700
Data Index: 1787949 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0674. Min Act: -0.1700
Data Index: 560248 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0674. Min Act: -0.1700
Data Index: 2092580 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0362. Min Act: -0.1700
Data Index: 2138890 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0362. Min Act: -0.1700
Data Index: 1567045 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0049. Min Act: -0.1700
Data Index: 6512078 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0049. Min Act: -0.1700
Data Index: 4731857 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0049. Min Act: -0.1700
Data Index: 6984093 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 3687757 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0049. Min Act: -0.1700
Data Index: 5663355 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0049. Min Act: -0.1700
Data Index: 8507713 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1612. Min Range: -4.1612
Max Act: 4.0049. Min Act: -0.1700
Data Index: 7783753 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 3275247 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 6192381 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 6663645 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9424. Min Act: -0.1700
Data Index: 5000706 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 1634819 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 7043403 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 1278498 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1612. Min Range: -4.1612
Max Act: 3.9737. Min Act: -0.1700
Data Index: 4475655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19