Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5534 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.3524. Min Act: -0.1700
Data Index: 5494800 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.2899. Min Act: -0.1700
Data Index: 3722696 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.2274. Min Act: -0.1700
Data Index: 5836540 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.1961. Min Act: -0.1700
Data Index: 427843 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.1961. Min Act: -0.1700
Data Index: 127064 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.1649. Min Act: -0.1700
Data Index: 939115 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3536535 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.1336. Min Act: -0.1700
Data Index: 4241503 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0711. Min Act: -0.1700
Data Index: 1000633 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0399. Min Act: -0.1700
Data Index: 3229113 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0399. Min Act: -0.1700
Data Index: 4865276 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0711. Min Act: -0.1700
Data Index: 4255834 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0711. Min Act: -0.1700
Data Index: 5365360 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0399. Min Act: -0.1700
Data Index: 2566958 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0399. Min Act: -0.1700
Data Index: 5589627 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0399. Min Act: -0.1700
Data Index: 7681283 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0086. Min Act: -0.1700
Data Index: 1946402 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0086. Min Act: -0.1700
Data Index: 4325680 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0399. Min Act: -0.1700
Data Index: 4489836 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3524. Min Range: -5.3524
Max Act: 5.0086. Min Act: -0.1700
Data Index: 7599853 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19