Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1299. Min Range: -4.1299
Max Act: 4.1299. Min Act: -0.1700
Data Index: 1628056 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1299. Min Range: -4.1299
Max Act: 4.0049. Min Act: -0.1700
Data Index: 6896746 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.9424. Min Act: -0.1700
Data Index: 8364643 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.9424. Min Act: -0.1700
Data Index: 8600080 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.8799. Min Act: -0.1700
Data Index: 906951 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.8799. Min Act: -0.1700
Data Index: 6668866 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.8799. Min Act: -0.1700
Data Index: 200747 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.8486. Min Act: -0.1700
Data Index: 1247591 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.8486. Min Act: -0.1700
Data Index: 7783179 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7860. Min Act: -0.1700
Data Index: 5734409 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7860. Min Act: -0.1700
Data Index: 1247592 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7860. Min Act: -0.1700
Data Index: 3494031 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7860. Min Act: -0.1700
Data Index: 2499725 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7860. Min Act: -0.1700
Data Index: 4681810 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7548. Min Act: -0.1700
Data Index: 2745855 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7548. Min Act: -0.1700
Data Index: 461675 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7548. Min Act: -0.1700
Data Index: 2527221 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.7548. Min Act: -0.1700
Data Index: 1602207 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.6922. Min Act: -0.1700
Data Index: 6059015 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1299. Min Range: -4.1299
Max Act: 3.6922. Min Act: -0.1700
Data Index: 3109970 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19