Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2220 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.9711. Min Act: -0.1700
Data Index: 2708035 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.9711. Min Act: -0.1700
Data Index: 1745374 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.9399. Min Act: -0.1700
Data Index: 2390310 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.9086. Min Act: -0.1700
Data Index: 6361167 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.8461. Min Act: -0.1700
Data Index: 3525472 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.8461. Min Act: -0.1700
Data Index: 3426386 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.8774. Min Act: -0.1700
Data Index: 5722583 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.7836. Min Act: -0.1700
Data Index: 3299304 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.8149. Min Act: -0.1700
Data Index: 8130247 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.8149. Min Act: -0.1700
Data Index: 6823847 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.7836. Min Act: -0.1700
Data Index: 261526 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.7836. Min Act: -0.1700
Data Index: 4394373 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.7836. Min Act: -0.1700
Data Index: 4889321 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.7836. Min Act: -0.1700
Data Index: 4655402 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.7211. Min Act: -0.1700
Data Index: 3008618 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.6899. Min Act: -0.1700
Data Index: 2905086 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.6899. Min Act: -0.1700
Data Index: 5248528 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.6899. Min Act: -0.1700
Data Index: 5262840 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.6586. Min Act: -0.1700
Data Index: 3008610 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9711. Min Range: -4.9711
Max Act: 4.6586. Min Act: -0.1700
Data Index: 3963039 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19