Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.9482. Min Act: -0.1700
Data Index: 6289357 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 1306822 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.9169. Min Act: -0.1700
Data Index: 8423680 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.9169. Min Act: -0.1700
Data Index: 1364687 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.9169. Min Act: -0.1700
Data Index: 5353954 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 5210428 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 6540887 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 1179169 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 6139048 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 6803890 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 2538011 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 929498 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 7789497 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 4511932 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8857. Min Act: -0.1700
Data Index: 802942 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8544. Min Act: -0.1700
Data Index: 7068637 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8544. Min Act: -0.1700
Data Index: 1979971 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8544. Min Act: -0.1700
Data Index: 1553655 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8544. Min Act: -0.1700
Data Index: 1486772 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9482. Min Range: -3.9482
Max Act: 3.8544. Min Act: -0.1700
Data Index: 5605328 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19