Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.2960. Min Act: -0.1700
Data Index: 1216518 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.2960. Min Act: -0.1700
Data Index: 4517807 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.2335. Min Act: -0.1700
Data Index: 1166317 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.2022. Min Act: -0.1700
Data Index: 6100962 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.2022. Min Act: -0.1700
Data Index: 144948 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1710. Min Act: -0.1700
Data Index: 6580630 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1397. Min Act: -0.1700
Data Index: 4751197 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1710. Min Act: -0.1700
Data Index: 3603999 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1710. Min Act: -0.1700
Data Index: 8201639 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1085. Min Act: -0.1700
Data Index: 1592180 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.0772. Min Act: -0.1700
Data Index: 6441568 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1085. Min Act: -0.1700
Data Index: 7702832 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2960. Min Range: -7.2960
Max Act: 7.1085. Min Act: -0.1700
Data Index: 3945273 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9835. Min Act: -0.1700
Data Index: 5138352 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9835. Min Act: -0.1700
Data Index: 4899422 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9835. Min Act: -0.1700
Data Index: 8065338 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9522. Min Act: -0.1700
Data Index: 2002431 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9210. Min Act: -0.1700
Data Index: 516879 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9522. Min Act: -0.1700
Data Index: 301657 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2960. Min Range: -7.2960
Max Act: 6.9210. Min Act: -0.1700
Data Index: 3328054 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19