Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.7080. Min Act: -0.1700
Data Index: 1653891 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.6143. Min Act: -0.1700
Data Index: 2887374 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.5830. Min Act: -0.1700
Data Index: 4116892 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.5518. Min Act: -0.1700
Data Index: 8277049 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.5205. Min Act: -0.1700
Data Index: 5797417 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.5205. Min Act: -0.1700
Data Index: 7248307 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.4580. Min Act: -0.1700
Data Index: 443213 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.4267. Min Act: -0.1700
Data Index: 8518543 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.4267. Min Act: -0.1700
Data Index: 8383839 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.4267. Min Act: -0.1700
Data Index: 3286531 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3955. Min Act: -0.1700
Data Index: 4726563 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3955. Min Act: -0.1700
Data Index: 443214 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3642. Min Act: -0.1700
Data Index: 375755 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3642. Min Act: -0.1700
Data Index: 6869082 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3642. Min Act: -0.1700
Data Index: 1988356 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3642. Min Act: -0.1700
Data Index: 8328088 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3330. Min Act: -0.1700
Data Index: 6899393 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3330. Min Act: -0.1700
Data Index: 6725053 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3017. Min Act: -0.1700
Data Index: 5138308 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7080. Min Range: -4.7080
Max Act: 4.3330. Min Act: -0.1700
Data Index: 3295359 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19