Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.4109. Min Act: -0.1700
Data Index: 8246758 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.2234. Min Act: -0.1700
Data Index: 8454682 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.1297. Min Act: -0.1700
Data Index: 6461507 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.1297. Min Act: -0.1700
Data Index: 2551731 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.0984. Min Act: -0.1700
Data Index: 8816468 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.0359. Min Act: -0.1700
Data Index: 8562863 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.9734. Min Act: -0.1700
Data Index: 2329614 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.9734. Min Act: -0.1700
Data Index: 6835955 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.9109. Min Act: -0.1700
Data Index: 2363075 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.9109. Min Act: -0.1700
Data Index: 4113352 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.8484. Min Act: -0.1700
Data Index: 7090103 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.7859. Min Act: -0.1700
Data Index: 5783351 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.7859. Min Act: -0.1700
Data Index: 1296047 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.7859. Min Act: -0.1700
Data Index: 7409060 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.7234. Min Act: -0.1700
Data Index: 439895 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.6922. Min Act: -0.1700
Data Index: 7060832 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.6609. Min Act: -0.1700
Data Index: 2069889 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.6609. Min Act: -0.1700
Data Index: 5821793 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.6297. Min Act: -0.1700
Data Index: 5708278 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.6297. Min Act: -0.1700
Data Index: 1602039 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19