Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.6404. Min Act: -0.1700
Data Index: 633061 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.6404. Min Act: -0.1700
Data Index: 7849618 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.5154. Min Act: -0.1700
Data Index: 1609970 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.4842. Min Act: -0.1700
Data Index: 4694344 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.3279. Min Act: -0.1700
Data Index: 8118300 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.2967. Min Act: -0.1700
Data Index: 7877096 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.3279. Min Act: -0.1700
Data Index: 6063871 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.2654. Min Act: -0.1700
Data Index: 6201681 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.2654. Min Act: -0.1700
Data Index: 178860 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.2342. Min Act: -0.1700
Data Index: 4807297 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1316022 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1717. Min Act: -0.1700
Data Index: 2245576 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1404. Min Act: -0.1700
Data Index: 3773172 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1634019 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1404. Min Act: -0.1700
Data Index: 8490210 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1092. Min Act: -0.1700
Data Index: 7740914 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.0779. Min Act: -0.1700
Data Index: 7491695 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.1092. Min Act: -0.1700
Data Index: 7117502 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.0467. Min Act: -0.1700
Data Index: 7839577 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6404. Min Range: -5.6404
Max Act: 5.0154. Min Act: -0.1700
Data Index: 505801 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19