Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6355 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.6836. Min Act: -0.1700
Data Index: 1513400 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.6836. Min Act: -0.1700
Data Index: 2219972 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.6523. Min Act: -0.1700
Data Index: 354808 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.5273. Min Act: -0.1700
Data Index: 4114689 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.5273. Min Act: -0.1700
Data Index: 4246326 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.5273. Min Act: -0.1700
Data Index: 567405 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4961. Min Act: -0.1700
Data Index: 3297157 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4961. Min Act: -0.1700
Data Index: 8578192 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4336. Min Act: -0.1700
Data Index: 2127765 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4648. Min Act: -0.1700
Data Index: 3166864 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4648. Min Act: -0.1700
Data Index: 7577326 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4648. Min Act: -0.1700
Data Index: 5559237 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4336. Min Act: -0.1700
Data Index: 6424568 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4336. Min Act: -0.1700
Data Index: 8234636 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4336. Min Act: -0.1700
Data Index: 5230843 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4336. Min Act: -0.1700
Data Index: 8765887 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4023. Min Act: -0.1700
Data Index: 4962253 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4023. Min Act: -0.1700
Data Index: 2840086 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4023. Min Act: -0.1700
Data Index: 4560236 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6836. Min Range: -5.6836
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7338419 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19