Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.9604. Min Act: -0.1700
Data Index: 6580003 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.4441. Min Act: -0.1700
Data Index: 2145748 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.4285. Min Act: -0.1700
Data Index: 3801671 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.3657. Min Act: -0.1700
Data Index: 643467 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.3344. Min Act: -0.1700
Data Index: 4409479 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.3187. Min Act: -0.1700
Data Index: 1887261 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2873. Min Act: -0.1700
Data Index: 8384547 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.3030. Min Act: -0.1700
Data Index: 2870544 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.3030. Min Act: -0.1700
Data Index: 1078823 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2873. Min Act: -0.1700
Data Index: 6566549 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2873. Min Act: -0.1700
Data Index: 5779136 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2716. Min Act: -0.1700
Data Index: 2286025 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2716. Min Act: -0.1700
Data Index: 7960435 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2559. Min Act: -0.1700
Data Index: 5941105 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2716. Min Act: -0.1700
Data Index: 7833080 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2559. Min Act: -0.1700
Data Index: 7799168 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2402. Min Act: -0.1700
Data Index: 5942140 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2559. Min Act: -0.1700
Data Index: 8651218 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2244. Min Act: -0.1700
Data Index: 8579876 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9604. Min Range: -3.9604
Max Act: 3.2402. Min Act: -0.1700
Data Index: 6713879 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19