Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 931 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1913. Min Range: -8.1913
Max Act: 8.1913. Min Act: -0.1700
Data Index: 3928795 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1913. Min Range: -8.1913
Max Act: 8.0663. Min Act: -0.1700
Data Index: 6126613 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1913. Min Range: -8.1913
Max Act: 8.0038. Min Act: -0.1700
Data Index: 7858618 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.9101. Min Act: -0.1700
Data Index: 489181 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.9101. Min Act: -0.1700
Data Index: 4350544 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.8163. Min Act: -0.1700
Data Index: 3064384 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.8163. Min Act: -0.1700
Data Index: 3467108 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.7851. Min Act: -0.1700
Data Index: 2442451 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.7538. Min Act: -0.1700
Data Index: 5440123 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.7538. Min Act: -0.1700
Data Index: 6165946 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.7226. Min Act: -0.1700
Data Index: 3438154 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.7226. Min Act: -0.1700
Data Index: 1646425 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.7538. Min Act: -0.1700
Data Index: 354184 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.6913. Min Act: -0.1700
Data Index: 3079667 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.6288. Min Act: -0.1700
Data Index: 3612548 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.5976. Min Act: -0.1700
Data Index: 8012802 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.5663. Min Act: -0.1700
Data Index: 1838673 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.5663. Min Act: -0.1700
Data Index: 584952 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.5663. Min Act: -0.1700
Data Index: 377258 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1913. Min Range: -8.1913
Max Act: 7.5663. Min Act: -0.1700
Data Index: 3456135 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19