Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.6158. Min Act: -0.1700
Data Index: 612235 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.4908. Min Act: -0.1700
Data Index: 7154622 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.5221. Min Act: -0.1700
Data Index: 1802389 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.3658. Min Act: -0.1700
Data Index: 1991024 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.3346. Min Act: -0.1700
Data Index: 433049 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.3033. Min Act: -0.1700
Data Index: 6576107 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.2408. Min Act: -0.1700
Data Index: 8511694 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.2096. Min Act: -0.1700
Data Index: 5344403 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.1471. Min Act: -0.1700
Data Index: 6635756 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.1471. Min Act: -0.1700
Data Index: 2115522 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.1471. Min Act: -0.1700
Data Index: 6856446 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.1158. Min Act: -0.1700
Data Index: 333558 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0846. Min Act: -0.1700
Data Index: 7421214 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0846. Min Act: -0.1700
Data Index: 7917285 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0846. Min Act: -0.1700
Data Index: 8150645 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0533. Min Act: -0.1700
Data Index: 1991027 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0533. Min Act: -0.1700
Data Index: 6291068 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0533. Min Act: -0.1700
Data Index: 7067639 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0846. Min Act: -0.1700
Data Index: 193079 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6158. Min Range: -6.6158
Max Act: 6.0533. Min Act: -0.1700
Data Index: 6891105 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19