Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5595 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.8534. Min Act: -0.1700
Data Index: 5138983 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.8534. Min Act: -0.1700
Data Index: 6708720 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.7283. Min Act: -0.1700
Data Index: 8007075 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.7283. Min Act: -0.1700
Data Index: 7341713 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6970. Min Act: -0.1700
Data Index: 694440 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6658. Min Act: -0.1700
Data Index: 1564306 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6970. Min Act: -0.1700
Data Index: 8255605 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6970. Min Act: -0.1700
Data Index: 4824065 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6658. Min Act: -0.1700
Data Index: 1746403 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 8807445 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6658. Min Act: -0.1700
Data Index: 3260022 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6658. Min Act: -0.1700
Data Index: 8557286 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6658. Min Act: -0.1700
Data Index: 7409929 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 8294181 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 4495769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6658. Min Act: -0.1700
Data Index: 7497500 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 7326133 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 2833278 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 6311383 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8534. Min Range: -3.8534
Max Act: 3.6345. Min Act: -0.1700
Data Index: 1171693 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19