Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1667. Min Range: -6.1667
Max Act: 6.1667. Min Act: -0.1700
Data Index: 1659283 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1667. Min Range: -6.1667
Max Act: 6.0105. Min Act: -0.1700
Data Index: 2246248 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.9480. Min Act: -0.1700
Data Index: 5825369 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.9167. Min Act: -0.1700
Data Index: 7012555 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.8542. Min Act: -0.1700
Data Index: 8430388 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7917. Min Act: -0.1700
Data Index: 2823733 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.8230. Min Act: -0.1700
Data Index: 2868489 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7917. Min Act: -0.1700
Data Index: 6008538 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7917. Min Act: -0.1700
Data Index: 4402158 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7917. Min Act: -0.1700
Data Index: 5482271 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7917. Min Act: -0.1700
Data Index: 776591 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7292. Min Act: -0.1700
Data Index: 543071 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7292. Min Act: -0.1700
Data Index: 4613535 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7292. Min Act: -0.1700
Data Index: 4988031 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7292. Min Act: -0.1700
Data Index: 5194223 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.7292. Min Act: -0.1700
Data Index: 3062347 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.6980. Min Act: -0.1700
Data Index: 8269663 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.6980. Min Act: -0.1700
Data Index: 5714782 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.6667. Min Act: -0.1700
Data Index: 5561884 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1667. Min Range: -6.1667
Max Act: 5.6667. Min Act: -0.1700
Data Index: 2573009 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19