Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 259 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.8098. Min Act: -0.1700
Data Index: 182553 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.7160. Min Act: -0.1700
Data Index: 5234372 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.6848. Min Act: -0.1700
Data Index: 3029179 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.5285. Min Act: -0.1700
Data Index: 1299930 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.4660. Min Act: -0.1700
Data Index: 3129760 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.4660. Min Act: -0.1700
Data Index: 576701 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3723. Min Act: -0.1700
Data Index: 2424001 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3723. Min Act: -0.1700
Data Index: 5489855 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3410. Min Act: -0.1700
Data Index: 6674211 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3098. Min Act: -0.1700
Data Index: 4648741 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3410. Min Act: -0.1700
Data Index: 686217 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3098. Min Act: -0.1700
Data Index: 4870283 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3098. Min Act: -0.1700
Data Index: 6502604 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 4445635 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.3098. Min Act: -0.1700
Data Index: 6729680 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 5036543 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 4576200 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 4218057 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 2044076 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8098. Min Range: -4.8098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 3332630 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19