Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4679 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2863. Min Range: -5.2863
Max Act: 5.2863. Min Act: -0.1700
Data Index: 4649077 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2863. Min Range: -5.2863
Max Act: 5.1613. Min Act: -0.1700
Data Index: 5638961 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2863. Min Range: -5.2863
Max Act: 5.0676. Min Act: -0.1700
Data Index: 2254697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2863. Min Range: -5.2863
Max Act: 5.0676. Min Act: -0.1700
Data Index: 8219140 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2863. Min Range: -5.2863
Max Act: 5.0676. Min Act: -0.1700
Data Index: 7585694 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.9426. Min Act: -0.1700
Data Index: 316336 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.9426. Min Act: -0.1700
Data Index: 8227353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.8176. Min Act: -0.1700
Data Index: 1344671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.8176. Min Act: -0.1700
Data Index: 1638706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.8176. Min Act: -0.1700
Data Index: 3900755 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.8176. Min Act: -0.1700
Data Index: 4470053 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 6450172 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7551. Min Act: -0.1700
Data Index: 6297189 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 4732077 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 4254342 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 8046194 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 6433413 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7551. Min Act: -0.1700
Data Index: 94313 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7551. Min Act: -0.1700
Data Index: 895470 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2863. Min Range: -5.2863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 568790 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19