Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7174. Min Range: -8.7174
Max Act: 8.7174. Min Act: -0.1700
Data Index: 6221681 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7174. Min Range: -8.7174
Max Act: 8.5299. Min Act: -0.1700
Data Index: 6258223 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7174. Min Range: -8.7174
Max Act: 8.0299. Min Act: -0.1700
Data Index: 3090266 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.9674. Min Act: -0.1700
Data Index: 7044604 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7174. Min Range: -8.7174
Max Act: 8.0299. Min Act: -0.1700
Data Index: 2799551 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.9049. Min Act: -0.1700
Data Index: 1307372 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.8424. Min Act: -0.1700
Data Index: 8779681 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.8424. Min Act: -0.1700
Data Index: 2175689 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.7174. Min Act: -0.1700
Data Index: 829393 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.7174. Min Act: -0.1700
Data Index: 7016833 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6862. Min Act: -0.1700
Data Index: 8176027 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6862. Min Act: -0.1700
Data Index: 1437196 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6549. Min Act: -0.1700
Data Index: 4674143 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6237. Min Act: -0.1700
Data Index: 5033238 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6237. Min Act: -0.1700
Data Index: 294497 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6237. Min Act: -0.1700
Data Index: 7555884 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6237. Min Act: -0.1700
Data Index: 1267900 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.6237. Min Act: -0.1700
Data Index: 2846003 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.5924. Min Act: -0.1700
Data Index: 7067796 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7174. Min Range: -8.7174
Max Act: 7.5924. Min Act: -0.1700
Data Index: 212134 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19