Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2119 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1956. Min Act: -0.1700
Data Index: 1531635 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1484. Min Act: -0.1700
Data Index: 69283 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1484. Min Act: -0.1700
Data Index: 7504360 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1169. Min Act: -0.1700
Data Index: 5284475 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1011. Min Act: -0.1700
Data Index: 7542489 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0854. Min Act: -0.1700
Data Index: 6876902 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1011. Min Act: -0.1700
Data Index: 5492851 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1011. Min Act: -0.1700
Data Index: 5795894 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.1011. Min Act: -0.1700
Data Index: 2631035 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0854. Min Act: -0.1700
Data Index: 2058610 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0854. Min Act: -0.1700
Data Index: 7270110 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0854. Min Act: -0.1700
Data Index: 1530310 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0696. Min Act: -0.1700
Data Index: 5503609 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0538. Min Act: -0.1700
Data Index: 6184126 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0380. Min Act: -0.1700
Data Index: 4028843 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0380. Min Act: -0.1700
Data Index: 158081 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0538. Min Act: -0.1700
Data Index: 1740290 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0380. Min Act: -0.1700
Data Index: 1289436 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0380. Min Act: -0.1700
Data Index: 7835823 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1956. Min Range: -3.1956
Max Act: 3.0380. Min Act: -0.1700
Data Index: 5678044 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19