Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4730 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.9272. Min Act: -0.1700
Data Index: 756676 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.8334. Min Act: -0.1700
Data Index: 8690627 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.8022. Min Act: -0.1700
Data Index: 3582067 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.8022. Min Act: -0.1700
Data Index: 991604 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.7709. Min Act: -0.1700
Data Index: 8576823 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.7397. Min Act: -0.1700
Data Index: 4695476 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.7397. Min Act: -0.1700
Data Index: 5401218 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.7084. Min Act: -0.1700
Data Index: 4438839 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5401221 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.6772. Min Act: -0.1700
Data Index: 7333949 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.6459. Min Act: -0.1700
Data Index: 4698835 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.6147. Min Act: -0.1700
Data Index: 7861875 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.6147. Min Act: -0.1700
Data Index: 4375465 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.6147. Min Act: -0.1700
Data Index: 4632782 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.5522. Min Act: -0.1700
Data Index: 4612201 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.5834. Min Act: -0.1700
Data Index: 3398109 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.5522. Min Act: -0.1700
Data Index: 8576820 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.5209. Min Act: -0.1700
Data Index: 8576821 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.4897. Min Act: -0.1700
Data Index: 494314 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9272. Min Range: -5.9272
Max Act: 5.5209. Min Act: -0.1700
Data Index: 909346 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19