Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.8076. Min Act: -0.1700
Data Index: 456975 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.5576. Min Act: -0.1700
Data Index: 2431664 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.5576. Min Act: -0.1700
Data Index: 1179776 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.5576. Min Act: -0.1700
Data Index: 4865061 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.4326. Min Act: -0.1700
Data Index: 4531115 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.4326. Min Act: -0.1700
Data Index: 1086020 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.4326. Min Act: -0.1700
Data Index: 3647682 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.3701. Min Act: -0.1700
Data Index: 975542 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.3076. Min Act: -0.1700
Data Index: 7356661 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.3076. Min Act: -0.1700
Data Index: 1539254 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.2451. Min Act: -0.1700
Data Index: 843028 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.2451. Min Act: -0.1700
Data Index: 3089550 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.2451. Min Act: -0.1700
Data Index: 6506520 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.1826. Min Act: -0.1700
Data Index: 6812245 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.1826. Min Act: -0.1700
Data Index: 873243 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.2451. Min Act: -0.1700
Data Index: 2278830 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.1826. Min Act: -0.1700
Data Index: 6112318 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.1201. Min Act: -0.1700
Data Index: 3243196 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.1201. Min Act: -0.1700
Data Index: 3566845 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8076. Min Range: -8.8076
Max Act: 8.1201. Min Act: -0.1700
Data Index: 774473 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19