Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.5572. Min Act: -0.1700
Data Index: 277876 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.4947. Min Act: -0.1700
Data Index: 4299104 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.3697. Min Act: -0.1700
Data Index: 3417336 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.3385. Min Act: -0.1700
Data Index: 5092638 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.3385. Min Act: -0.1700
Data Index: 3211858 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.3072. Min Act: -0.1700
Data Index: 8760343 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.3072. Min Act: -0.1700
Data Index: 7366238 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2760. Min Act: -0.1700
Data Index: 5141169 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2760. Min Act: -0.1700
Data Index: 6804192 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2760. Min Act: -0.1700
Data Index: 7361211 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2447. Min Act: -0.1700
Data Index: 17019 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2447. Min Act: -0.1700
Data Index: 1231150 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2135. Min Act: -0.1700
Data Index: 871436 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2135. Min Act: -0.1700
Data Index: 5981454 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2135. Min Act: -0.1700
Data Index: 8195509 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2135. Min Act: -0.1700
Data Index: 872996 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.2447. Min Act: -0.1700
Data Index: 4957708 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.1822. Min Act: -0.1700
Data Index: 189263 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.1822. Min Act: -0.1700
Data Index: 2529793 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5572. Min Range: -6.5572
Max Act: 6.1822. Min Act: -0.1700
Data Index: 2492837 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19