Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.4548. Min Act: -0.1700
Data Index: 8010134 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.2047. Min Act: -0.1700
Data Index: 2036067 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.1422. Min Act: -0.1700
Data Index: 2075626 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0797. Min Act: -0.1700
Data Index: 6505194 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 3711414 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 7130360 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0485. Min Act: -0.1700
Data Index: 7051831 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0485. Min Act: -0.1700
Data Index: 6766641 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 3877074 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 6658326 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 5057996 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9859. Min Act: -0.1700
Data Index: 8509957 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 215414 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9859. Min Act: -0.1700
Data Index: 1883468 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4548. Min Range: -4.4548
Max Act: 4.0172. Min Act: -0.1700
Data Index: 7530135 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9859. Min Act: -0.1700
Data Index: 637972 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9859. Min Act: -0.1700
Data Index: 2006780 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9859. Min Act: -0.1700
Data Index: 442338 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9859. Min Act: -0.1700
Data Index: 6924573 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4548. Min Range: -4.4548
Max Act: 3.9547. Min Act: -0.1700
Data Index: 4362346 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19