Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.8987. Min Act: -0.1700
Data Index: 2853241 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6800. Min Act: -0.1700
Data Index: 8480349 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6487. Min Act: -0.1700
Data Index: 7127883 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6487. Min Act: -0.1700
Data Index: 1944421 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6487. Min Act: -0.1700
Data Index: 1870173 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6487. Min Act: -0.1700
Data Index: 3328201 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6175. Min Act: -0.1700
Data Index: 4856056 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.6175. Min Act: -0.1700
Data Index: 4624355 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5862. Min Act: -0.1700
Data Index: 8150031 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5862. Min Act: -0.1700
Data Index: 2346533 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5862. Min Act: -0.1700
Data Index: 5228585 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5550. Min Act: -0.1700
Data Index: 8393912 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5550. Min Act: -0.1700
Data Index: 4969725 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5237. Min Act: -0.1700
Data Index: 152445 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5237. Min Act: -0.1700
Data Index: 1916048 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5237. Min Act: -0.1700
Data Index: 1617782 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.5237. Min Act: -0.1700
Data Index: 1510203 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.4925. Min Act: -0.1700
Data Index: 1089904 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.4925. Min Act: -0.1700
Data Index: 2415671 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8987. Min Range: -5.8987
Max Act: 5.4925. Min Act: -0.1700
Data Index: 3459774 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19