Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.6434. Min Act: -0.1700
Data Index: 3698357 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.6434. Min Act: -0.1700
Data Index: 7692989 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.6434. Min Act: -0.1700
Data Index: 7400613 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.6434. Min Act: -0.1700
Data Index: 7428705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.5497. Min Act: -0.1700
Data Index: 1421888 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4872. Min Act: -0.1700
Data Index: 6387502 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.5184. Min Act: -0.1700
Data Index: 2973720 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4872. Min Act: -0.1700
Data Index: 2087294 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 1670712 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 689620 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4559. Min Act: -0.1700
Data Index: 8587633 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 3338142 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 2254208 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 7743417 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 6721105 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.4247. Min Act: -0.1700
Data Index: 6363528 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.3934. Min Act: -0.1700
Data Index: 5618979 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.3622. Min Act: -0.1700
Data Index: 5428483 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.3622. Min Act: -0.1700
Data Index: 3572535 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6434. Min Range: -4.6434
Max Act: 4.3622. Min Act: -0.1700
Data Index: 3639668 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19