Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.5586. Min Act: -0.1700
Data Index: 140979 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.4961. Min Act: -0.1700
Data Index: 3311141 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.4961. Min Act: -0.1700
Data Index: 504496 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.4336. Min Act: -0.1700
Data Index: 77958 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.4024. Min Act: -0.1700
Data Index: 5288001 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.3399. Min Act: -0.1700
Data Index: 7865335 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.3086. Min Act: -0.1700
Data Index: 4122313 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.3086. Min Act: -0.1700
Data Index: 4346917 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 2780805 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.3086. Min Act: -0.1700
Data Index: 4768752 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 2384775 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 3613552 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 4777260 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 19563 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 7024418 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2774. Min Act: -0.1700
Data Index: 4346918 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2461. Min Act: -0.1700
Data Index: 865498 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2461. Min Act: -0.1700
Data Index: 4250276 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2461. Min Act: -0.1700
Data Index: 3451141 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5586. Min Range: -4.5586
Max Act: 4.2461. Min Act: -0.1700
Data Index: 4688828 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19