Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5203 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.8137. Min Act: -0.1700
Data Index: 5713129 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.5325. Min Act: -0.1700
Data Index: 2377215 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.5012. Min Act: -0.1700
Data Index: 4267933 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.4387. Min Act: -0.1700
Data Index: 7188886 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.4075. Min Act: -0.1700
Data Index: 183472 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.3762. Min Act: -0.1700
Data Index: 380487 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.3762. Min Act: -0.1700
Data Index: 8546530 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.3762. Min Act: -0.1700
Data Index: 4239976 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3486794 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.2825. Min Act: -0.1700
Data Index: 10471 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.2825. Min Act: -0.1700
Data Index: 3595201 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.3137. Min Act: -0.1700
Data Index: 852248 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.2512. Min Act: -0.1700
Data Index: 6282727 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.2512. Min Act: -0.1700
Data Index: 5394598 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.2200. Min Act: -0.1700
Data Index: 5641504 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.1887. Min Act: -0.1700
Data Index: 4459951 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.2200. Min Act: -0.1700
Data Index: 8583125 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.1887. Min Act: -0.1700
Data Index: 1284437 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.1887. Min Act: -0.1700
Data Index: 6916848 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8137. Min Range: -5.8137
Max Act: 5.1887. Min Act: -0.1700
Data Index: 258075 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19