Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.8140. Min Act: -0.1700
Data Index: 594667 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.5952. Min Act: -0.1700
Data Index: 8280022 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.5640. Min Act: -0.1700
Data Index: 1776821 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.4702. Min Act: -0.1700
Data Index: 2214322 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.4390. Min Act: -0.1700
Data Index: 2745505 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.4077. Min Act: -0.1700
Data Index: 3365700 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.3452. Min Act: -0.1700
Data Index: 4050752 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.3140. Min Act: -0.1700
Data Index: 8374797 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.3140. Min Act: -0.1700
Data Index: 1353924 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.2515. Min Act: -0.1700
Data Index: 2994881 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.2515. Min Act: -0.1700
Data Index: 3743001 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.2202. Min Act: -0.1700
Data Index: 4383005 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.2202. Min Act: -0.1700
Data Index: 2678082 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.2202. Min Act: -0.1700
Data Index: 7913911 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.1890. Min Act: -0.1700
Data Index: 3828695 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.1890. Min Act: -0.1700
Data Index: 5778519 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.1265. Min Act: -0.1700
Data Index: 1024662 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.1890. Min Act: -0.1700
Data Index: 3816107 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.1265. Min Act: -0.1700
Data Index: 5160263 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8140. Min Range: -6.8140
Max Act: 6.1265. Min Act: -0.1700
Data Index: 8031888 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19