Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2750 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.7520. Min Act: -0.1700
Data Index: 8006760 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.6895. Min Act: -0.1700
Data Index: 2400728 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.5333. Min Act: -0.1700
Data Index: 5238526 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.4083. Min Act: -0.1700
Data Index: 6440389 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.4083. Min Act: -0.1700
Data Index: 4793861 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.4395. Min Act: -0.1700
Data Index: 1556254 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.3770. Min Act: -0.1700
Data Index: 7747949 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.3145. Min Act: -0.1700
Data Index: 1205024 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.3145. Min Act: -0.1700
Data Index: 5598750 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2833. Min Act: -0.1700
Data Index: 4703034 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2833. Min Act: -0.1700
Data Index: 2442830 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2833. Min Act: -0.1700
Data Index: 5024346 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2833. Min Act: -0.1700
Data Index: 2640635 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2520. Min Act: -0.1700
Data Index: 1323816 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2208. Min Act: -0.1700
Data Index: 2812876 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2520. Min Act: -0.1700
Data Index: 8366464 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.2208. Min Act: -0.1700
Data Index: 1159254 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.1895. Min Act: -0.1700
Data Index: 5087592 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.1583. Min Act: -0.1700
Data Index: 4101416 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7520. Min Range: -7.7520
Max Act: 7.1583. Min Act: -0.1700
Data Index: 3637752 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19