Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6256 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1336. Min Range: -6.1336
Max Act: 6.1336. Min Act: -0.1700
Data Index: 71845 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1336. Min Range: -6.1336
Max Act: 6.0086. Min Act: -0.1700
Data Index: 6566523 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9773. Min Act: -0.1700
Data Index: 6586832 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9461. Min Act: -0.1700
Data Index: 4298596 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9461. Min Act: -0.1700
Data Index: 8334679 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9148. Min Act: -0.1700
Data Index: 3905375 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9148. Min Act: -0.1700
Data Index: 5821329 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9148. Min Act: -0.1700
Data Index: 4563413 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9148. Min Act: -0.1700
Data Index: 1070745 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.9148. Min Act: -0.1700
Data Index: 7431452 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8836. Min Act: -0.1700
Data Index: 1771071 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8836. Min Act: -0.1700
Data Index: 2739648 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8523. Min Act: -0.1700
Data Index: 168607 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8836. Min Act: -0.1700
Data Index: 2665062 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8836. Min Act: -0.1700
Data Index: 2243387 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2456495 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8523. Min Act: -0.1700
Data Index: 312837 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8523. Min Act: -0.1700
Data Index: 6447934 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8211. Min Act: -0.1700
Data Index: 3134569 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1336. Min Range: -6.1336
Max Act: 5.8211. Min Act: -0.1700
Data Index: 5650358 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19