Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.6355. Min Act: -0.1700
Data Index: 3667623 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.5259. Min Act: -0.1700
Data Index: 1581005 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.5259. Min Act: -0.1700
Data Index: 4096268 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4946. Min Act: -0.1700
Data Index: 2472178 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.5259. Min Act: -0.1700
Data Index: 937655 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4946. Min Act: -0.1700
Data Index: 7290069 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4946. Min Act: -0.1700
Data Index: 1632005 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4633. Min Act: -0.1700
Data Index: 3559537 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4476. Min Act: -0.1700
Data Index: 6046643 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4319. Min Act: -0.1700
Data Index: 2548943 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4319. Min Act: -0.1700
Data Index: 3055823 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4319. Min Act: -0.1700
Data Index: 3450547 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4163. Min Act: -0.1700
Data Index: 3355933 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4163. Min Act: -0.1700
Data Index: 6906162 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4163. Min Act: -0.1700
Data Index: 386159 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4163. Min Act: -0.1700
Data Index: 714533 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4163. Min Act: -0.1700
Data Index: 937646 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.3849. Min Act: -0.1700
Data Index: 2200762 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4006. Min Act: -0.1700
Data Index: 639650 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6355. Min Range: -3.6355
Max Act: 3.4006. Min Act: -0.1700
Data Index: 7243052 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19