Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.7801. Min Act: -0.1700
Data Index: 3483998 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.7176. Min Act: -0.1700
Data Index: 7749489 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.6238. Min Act: -0.1700
Data Index: 5114514 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4676. Min Act: -0.1700
Data Index: 2145301 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4676. Min Act: -0.1700
Data Index: 6672715 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4363. Min Act: -0.1700
Data Index: 2397708 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4363. Min Act: -0.1700
Data Index: 8410452 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 2541667 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3426. Min Act: -0.1700
Data Index: 7593897 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3426. Min Act: -0.1700
Data Index: 2541661 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2488. Min Act: -0.1700
Data Index: 8363486 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3113. Min Act: -0.1700
Data Index: 5608355 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2176. Min Act: -0.1700
Data Index: 8789088 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2488. Min Act: -0.1700
Data Index: 7617658 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2488. Min Act: -0.1700
Data Index: 757980 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2488. Min Act: -0.1700
Data Index: 4334620 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2176. Min Act: -0.1700
Data Index: 4451190 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.1863. Min Act: -0.1700
Data Index: 6063653 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.1863. Min Act: -0.1700
Data Index: 1496210 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.2176. Min Act: -0.1700
Data Index: 2541671 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19