Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2303 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1819. Min Range: -7.1819
Max Act: 7.1819. Min Act: -0.1700
Data Index: 1903549 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.9944. Min Act: -0.1700
Data Index: 7757274 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.9944. Min Act: -0.1700
Data Index: 2156433 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.8694. Min Act: -0.1700
Data Index: 894107 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.8381. Min Act: -0.1700
Data Index: 6507810 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.8381. Min Act: -0.1700
Data Index: 5877671 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.8069. Min Act: -0.1700
Data Index: 8753442 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.8069. Min Act: -0.1700
Data Index: 669437 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.7131. Min Act: -0.1700
Data Index: 8112401 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6194. Min Act: -0.1700
Data Index: 5568232 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6506. Min Act: -0.1700
Data Index: 6268387 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7757262 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6506. Min Act: -0.1700
Data Index: 4310585 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7332862 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6506. Min Act: -0.1700
Data Index: 3788674 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6194. Min Act: -0.1700
Data Index: 3152686 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6194. Min Act: -0.1700
Data Index: 6768370 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6194. Min Act: -0.1700
Data Index: 317352 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.6194. Min Act: -0.1700
Data Index: 8527771 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1819. Min Range: -7.1819
Max Act: 6.5881. Min Act: -0.1700
Data Index: 404890 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19