Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1118. Min Range: -5.1118
Max Act: 5.1118. Min Act: -0.1700
Data Index: 5595219 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1118. Min Range: -5.1118
Max Act: 5.0181. Min Act: -0.1700
Data Index: 2769351 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1118. Min Range: -5.1118
Max Act: 5.0181. Min Act: -0.1700
Data Index: 3312187 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.9243. Min Act: -0.1700
Data Index: 8719677 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.8618. Min Act: -0.1700
Data Index: 4644236 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.8618. Min Act: -0.1700
Data Index: 939454 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.8306. Min Act: -0.1700
Data Index: 1553512 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.8306. Min Act: -0.1700
Data Index: 1076381 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.8306. Min Act: -0.1700
Data Index: 756169 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7778323 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7993. Min Act: -0.1700
Data Index: 6161043 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7993. Min Act: -0.1700
Data Index: 5814577 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7993. Min Act: -0.1700
Data Index: 817829 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7681. Min Act: -0.1700
Data Index: 6134264 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7681. Min Act: -0.1700
Data Index: 1084096 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7368. Min Act: -0.1700
Data Index: 3276949 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7681. Min Act: -0.1700
Data Index: 1532471 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7368. Min Act: -0.1700
Data Index: 1155854 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7368. Min Act: -0.1700
Data Index: 2742567 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1118. Min Range: -5.1118
Max Act: 4.7368. Min Act: -0.1700
Data Index: 3324311 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19