Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.5658. Min Act: -0.1700
Data Index: 5071271 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.5345. Min Act: -0.1700
Data Index: 1774033 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.5345. Min Act: -0.1700
Data Index: 5071268 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.4720. Min Act: -0.1700
Data Index: 7990707 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.4408. Min Act: -0.1700
Data Index: 2593783 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.4095. Min Act: -0.1700
Data Index: 1986181 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.3782. Min Act: -0.1700
Data Index: 1968028 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.3157. Min Act: -0.1700
Data Index: 1697139 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.3157. Min Act: -0.1700
Data Index: 6842198 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.2220. Min Act: -0.1700
Data Index: 1151996 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.2532. Min Act: -0.1700
Data Index: 71665 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.2220. Min Act: -0.1700
Data Index: 7500443 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1907. Min Act: -0.1700
Data Index: 85524 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.2220. Min Act: -0.1700
Data Index: 8152595 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1907. Min Act: -0.1700
Data Index: 453458 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1907. Min Act: -0.1700
Data Index: 4438036 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1907. Min Act: -0.1700
Data Index: 2388473 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1907. Min Act: -0.1700
Data Index: 1228371 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1595. Min Act: -0.1700
Data Index: 2976897 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5658. Min Range: -4.5658
Max Act: 4.1595. Min Act: -0.1700
Data Index: 5167536 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19